edit

Towards Machine Learning Systems Design

$$\newcommand{\tk}[1]{} \newcommand{\Amatrix}{\mathbf{A}} \newcommand{\KL}[2]{\text{KL}\left( #1\,\|\,#2 \right)} \newcommand{\Kaast}{\kernelMatrix_{\mathbf{ \ast}\mathbf{ \ast}}} \newcommand{\Kastu}{\kernelMatrix_{\mathbf{ \ast} \inducingVector}} \newcommand{\Kff}{\kernelMatrix_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\Kfu}{\kernelMatrix_{\mappingFunctionVector \inducingVector}} \newcommand{\Kuast}{\kernelMatrix_{\inducingVector \bf\ast}} \newcommand{\Kuf}{\kernelMatrix_{\inducingVector \mappingFunctionVector}} \newcommand{\Kuu}{\kernelMatrix_{\inducingVector \inducingVector}} \newcommand{\Kuui}{\Kuu^{-1}} \newcommand{\Qaast}{\mathbf{Q}_{\bf \ast \ast}} \newcommand{\Qastf}{\mathbf{Q}_{\ast \mappingFunction}} \newcommand{\Qfast}{\mathbf{Q}_{\mappingFunctionVector \bf \ast}} \newcommand{\Qff}{\mathbf{Q}_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\aMatrix}{\mathbf{A}} \newcommand{\aScalar}{a} \newcommand{\aVector}{\mathbf{a}} \newcommand{\acceleration}{a} \newcommand{\bMatrix}{\mathbf{B}} \newcommand{\bScalar}{b} \newcommand{\bVector}{\mathbf{b}} \newcommand{\basisFunc}{\phi} \newcommand{\basisFuncVector}{\boldsymbol{ \basisFunc}} \newcommand{\basisFunction}{\phi} \newcommand{\basisLocation}{\mu} \newcommand{\basisMatrix}{\boldsymbol{ \Phi}} \newcommand{\basisScalar}{\basisFunction} \newcommand{\basisVector}{\boldsymbol{ \basisFunction}} \newcommand{\activationFunction}{\phi} \newcommand{\activationMatrix}{\boldsymbol{ \Phi}} \newcommand{\activationScalar}{\basisFunction} \newcommand{\activationVector}{\boldsymbol{ \basisFunction}} \newcommand{\bigO}{\mathcal{O}} \newcommand{\binomProb}{\pi} \newcommand{\cMatrix}{\mathbf{C}} \newcommand{\cbasisMatrix}{\hat{\boldsymbol{ \Phi}}} \newcommand{\cdataMatrix}{\hat{\dataMatrix}} \newcommand{\cdataScalar}{\hat{\dataScalar}} \newcommand{\cdataVector}{\hat{\dataVector}} \newcommand{\centeredKernelMatrix}{\mathbf{ \MakeUppercase{\centeredKernelScalar}}} \newcommand{\centeredKernelScalar}{b} \newcommand{\centeredKernelVector}{\centeredKernelScalar} \newcommand{\centeringMatrix}{\mathbf{H}} \newcommand{\chiSquaredDist}[2]{\chi_{#1}^{2}\left(#2\right)} \newcommand{\chiSquaredSamp}[1]{\chi_{#1}^{2}} \newcommand{\conditionalCovariance}{\boldsymbol{ \Sigma}} \newcommand{\coregionalizationMatrix}{\mathbf{B}} \newcommand{\coregionalizationScalar}{b} \newcommand{\coregionalizationVector}{\mathbf{ \coregionalizationScalar}} \newcommand{\covDist}[2]{\text{cov}_{#2}\left(#1\right)} \newcommand{\covSamp}[1]{\text{cov}\left(#1\right)} \newcommand{\covarianceScalar}{c} \newcommand{\covarianceVector}{\mathbf{ \covarianceScalar}} \newcommand{\covarianceMatrix}{\mathbf{C}} \newcommand{\covarianceMatrixTwo}{\boldsymbol{ \Sigma}} \newcommand{\croupierScalar}{s} \newcommand{\croupierVector}{\mathbf{ \croupierScalar}} \newcommand{\croupierMatrix}{\mathbf{ \MakeUppercase{\croupierScalar}}} \newcommand{\dataDim}{p} \newcommand{\dataIndex}{i} \newcommand{\dataIndexTwo}{j} \newcommand{\dataMatrix}{\mathbf{Y}} \newcommand{\dataScalar}{y} \newcommand{\dataSet}{\mathcal{D}} \newcommand{\dataStd}{\sigma} \newcommand{\dataVector}{\mathbf{ \dataScalar}} \newcommand{\decayRate}{d} \newcommand{\degreeMatrix}{\mathbf{ \MakeUppercase{\degreeScalar}}} \newcommand{\degreeScalar}{d} \newcommand{\degreeVector}{\mathbf{ \degreeScalar}} \newcommand{\diag}[1]{\text{diag}\left(#1\right)} \newcommand{\diagonalMatrix}{\mathbf{D}} \newcommand{\diff}[2]{\frac{\text{d}#1}{\text{d}#2}} \newcommand{\diffTwo}[2]{\frac{\text{d}^2#1}{\text{d}#2^2}} \newcommand{\displacement}{x} \newcommand{\displacementVector}{\textbf{\displacement}} \newcommand{\distanceMatrix}{\mathbf{ \MakeUppercase{\distanceScalar}}} \newcommand{\distanceScalar}{d} \newcommand{\distanceVector}{\mathbf{ \distanceScalar}} \newcommand{\eigenvaltwo}{\ell} \newcommand{\eigenvaltwoMatrix}{\mathbf{L}} \newcommand{\eigenvaltwoVector}{\mathbf{l}} \newcommand{\eigenvalue}{\lambda} \newcommand{\eigenvalueMatrix}{\boldsymbol{ \Lambda}} \newcommand{\eigenvalueVector}{\boldsymbol{ \lambda}} \newcommand{\eigenvector}{\mathbf{ \eigenvectorScalar}} \newcommand{\eigenvectorMatrix}{\mathbf{U}} \newcommand{\eigenvectorScalar}{u} \newcommand{\eigenvectwo}{\mathbf{v}} \newcommand{\eigenvectwoMatrix}{\mathbf{V}} \newcommand{\eigenvectwoScalar}{v} \newcommand{\entropy}[1]{\mathcal{H}\left(#1\right)} \newcommand{\errorFunction}{E} \newcommand{\expDist}[2]{\left\langle#1\right\rangle_{#2}} \newcommand{\expSamp}[1]{\left\langle#1\right\rangle} \newcommand{\expectation}[1]{\left\langle #1 \right\rangle } \newcommand{\expectationDist}[2]{\left\langle #1 \right\rangle _{#2}} \newcommand{\expectedDistanceMatrix}{\mathcal{D}} \newcommand{\eye}{\mathbf{I}} \newcommand{\fantasyDim}{r} \newcommand{\fantasyMatrix}{\mathbf{ \MakeUppercase{\fantasyScalar}}} \newcommand{\fantasyScalar}{z} \newcommand{\fantasyVector}{\mathbf{ \fantasyScalar}} \newcommand{\featureStd}{\varsigma} \newcommand{\gammaCdf}[3]{\mathcal{GAMMA CDF}\left(#1|#2,#3\right)} \newcommand{\gammaDist}[3]{\mathcal{G}\left(#1|#2,#3\right)} \newcommand{\gammaSamp}[2]{\mathcal{G}\left(#1,#2\right)} \newcommand{\gaussianDist}[3]{\mathcal{N}\left(#1|#2,#3\right)} \newcommand{\gaussianSamp}[2]{\mathcal{N}\left(#1,#2\right)} \newcommand{\uniformDist}[3]{\mathcal{U}\left(#1|#2,#3\right)} \newcommand{\uniformSamp}[2]{\mathcal{U}\left(#1,#2\right)} \newcommand{\given}{|} \newcommand{\half}{\frac{1}{2}} \newcommand{\heaviside}{H} \newcommand{\hiddenMatrix}{\mathbf{ \MakeUppercase{\hiddenScalar}}} \newcommand{\hiddenScalar}{h} \newcommand{\hiddenVector}{\mathbf{ \hiddenScalar}} \newcommand{\identityMatrix}{\eye} \newcommand{\inducingInputScalar}{z} \newcommand{\inducingInputVector}{\mathbf{ \inducingInputScalar}} \newcommand{\inducingInputMatrix}{\mathbf{Z}} \newcommand{\inducingScalar}{u} \newcommand{\inducingVector}{\mathbf{ \inducingScalar}} \newcommand{\inducingMatrix}{\mathbf{U}} \newcommand{\inlineDiff}[2]{\text{d}#1/\text{d}#2} \newcommand{\inputDim}{q} \newcommand{\inputMatrix}{\mathbf{X}} \newcommand{\inputScalar}{x} \newcommand{\inputSpace}{\mathcal{X}} \newcommand{\inputVals}{\inputVector} \newcommand{\inputVector}{\mathbf{ \inputScalar}} \newcommand{\iterNum}{k} \newcommand{\kernel}{\kernelScalar} \newcommand{\kernelMatrix}{\mathbf{K}} \newcommand{\kernelScalar}{k} \newcommand{\kernelVector}{\mathbf{ \kernelScalar}} \newcommand{\kff}{\kernelScalar_{\mappingFunction \mappingFunction}} \newcommand{\kfu}{\kernelVector_{\mappingFunction \inducingScalar}} \newcommand{\kuf}{\kernelVector_{\inducingScalar \mappingFunction}} \newcommand{\kuu}{\kernelVector_{\inducingScalar \inducingScalar}} \newcommand{\lagrangeMultiplier}{\lambda} \newcommand{\lagrangeMultiplierMatrix}{\boldsymbol{ \Lambda}} \newcommand{\lagrangian}{L} \newcommand{\laplacianFactor}{\mathbf{ \MakeUppercase{\laplacianFactorScalar}}} \newcommand{\laplacianFactorScalar}{m} \newcommand{\laplacianFactorVector}{\mathbf{ \laplacianFactorScalar}} \newcommand{\laplacianMatrix}{\mathbf{L}} \newcommand{\laplacianScalar}{\ell} \newcommand{\laplacianVector}{\mathbf{ \ell}} \newcommand{\latentDim}{q} \newcommand{\latentDistanceMatrix}{\boldsymbol{ \Delta}} \newcommand{\latentDistanceScalar}{\delta} \newcommand{\latentDistanceVector}{\boldsymbol{ \delta}} \newcommand{\latentForce}{f} \newcommand{\latentFunction}{u} \newcommand{\latentFunctionVector}{\mathbf{ \latentFunction}} \newcommand{\latentFunctionMatrix}{\mathbf{ \MakeUppercase{\latentFunction}}} \newcommand{\latentIndex}{j} \newcommand{\latentScalar}{z} \newcommand{\latentVector}{\mathbf{ \latentScalar}} \newcommand{\latentMatrix}{\mathbf{Z}} \newcommand{\learnRate}{\eta} \newcommand{\lengthScale}{\ell} \newcommand{\rbfWidth}{\ell} \newcommand{\likelihoodBound}{\mathcal{L}} \newcommand{\likelihoodFunction}{L} \newcommand{\locationScalar}{\mu} \newcommand{\locationVector}{\boldsymbol{ \locationScalar}} \newcommand{\locationMatrix}{\mathbf{M}} \newcommand{\variance}[1]{\text{var}\left( #1 \right)} \newcommand{\mappingFunction}{f} \newcommand{\mappingFunctionMatrix}{\mathbf{F}} \newcommand{\mappingFunctionTwo}{g} \newcommand{\mappingFunctionTwoMatrix}{\mathbf{G}} \newcommand{\mappingFunctionTwoVector}{\mathbf{ \mappingFunctionTwo}} \newcommand{\mappingFunctionVector}{\mathbf{ \mappingFunction}} \newcommand{\scaleScalar}{s} \newcommand{\mappingScalar}{w} \newcommand{\mappingVector}{\mathbf{ \mappingScalar}} \newcommand{\mappingMatrix}{\mathbf{W}} \newcommand{\mappingScalarTwo}{v} \newcommand{\mappingVectorTwo}{\mathbf{ \mappingScalarTwo}} \newcommand{\mappingMatrixTwo}{\mathbf{V}} \newcommand{\maxIters}{K} \newcommand{\meanMatrix}{\mathbf{M}} \newcommand{\meanScalar}{\mu} \newcommand{\meanTwoMatrix}{\mathbf{M}} \newcommand{\meanTwoScalar}{m} \newcommand{\meanTwoVector}{\mathbf{ \meanTwoScalar}} \newcommand{\meanVector}{\boldsymbol{ \meanScalar}} \newcommand{\mrnaConcentration}{m} \newcommand{\naturalFrequency}{\omega} \newcommand{\neighborhood}[1]{\mathcal{N}\left( #1 \right)} \newcommand{\neilurl}{http://inverseprobability.com/} \newcommand{\noiseMatrix}{\boldsymbol{ E}} \newcommand{\noiseScalar}{\epsilon} \newcommand{\noiseVector}{\boldsymbol{ \epsilon}} \newcommand{\noiseStd}{\sigma} \newcommand{\norm}[1]{\left\Vert #1 \right\Vert} \newcommand{\normalizedLaplacianMatrix}{\hat{\mathbf{L}}} \newcommand{\normalizedLaplacianScalar}{\hat{\ell}} \newcommand{\normalizedLaplacianVector}{\hat{\mathbf{ \ell}}} \newcommand{\numActive}{m} \newcommand{\numBasisFunc}{m} \newcommand{\numComponents}{m} \newcommand{\numComps}{K} \newcommand{\numData}{n} \newcommand{\numFeatures}{K} \newcommand{\numHidden}{h} \newcommand{\numInducing}{m} \newcommand{\numLayers}{\ell} \newcommand{\numNeighbors}{K} \newcommand{\numSequences}{s} \newcommand{\numSuccess}{s} \newcommand{\numTasks}{m} \newcommand{\numTime}{T} \newcommand{\numTrials}{S} \newcommand{\outputIndex}{j} \newcommand{\paramVector}{\boldsymbol{ \theta}} \newcommand{\parameterMatrix}{\boldsymbol{ \Theta}} \newcommand{\parameterScalar}{\theta} \newcommand{\parameterVector}{\boldsymbol{ \parameterScalar}} \newcommand{\partDiff}[2]{\frac{\partial#1}{\partial#2}} \newcommand{\precisionScalar}{j} \newcommand{\precisionVector}{\mathbf{ \precisionScalar}} \newcommand{\precisionMatrix}{\mathbf{J}} \newcommand{\pseudotargetScalar}{\widetilde{y}} \newcommand{\pseudotargetVector}{\mathbf{ \pseudotargetScalar}} \newcommand{\pseudotargetMatrix}{\mathbf{ \widetilde{Y}}} \newcommand{\rank}[1]{\text{rank}\left(#1\right)} \newcommand{\rayleighDist}[2]{\mathcal{R}\left(#1|#2\right)} \newcommand{\rayleighSamp}[1]{\mathcal{R}\left(#1\right)} \newcommand{\responsibility}{r} \newcommand{\rotationScalar}{r} \newcommand{\rotationVector}{\mathbf{ \rotationScalar}} \newcommand{\rotationMatrix}{\mathbf{R}} \newcommand{\sampleCovScalar}{s} \newcommand{\sampleCovVector}{\mathbf{ \sampleCovScalar}} \newcommand{\sampleCovMatrix}{\mathbf{s}} \newcommand{\scalarProduct}[2]{\left\langle{#1},{#2}\right\rangle} \newcommand{\sign}[1]{\text{sign}\left(#1\right)} \newcommand{\sigmoid}[1]{\sigma\left(#1\right)} \newcommand{\singularvalue}{\ell} \newcommand{\singularvalueMatrix}{\mathbf{L}} \newcommand{\singularvalueVector}{\mathbf{l}} \newcommand{\sorth}{\mathbf{u}} \newcommand{\spar}{\lambda} \newcommand{\trace}[1]{\text{tr}\left(#1\right)} \newcommand{\BasalRate}{B} \newcommand{\DampingCoefficient}{C} \newcommand{\DecayRate}{D} \newcommand{\Displacement}{X} \newcommand{\LatentForce}{F} \newcommand{\Mass}{M} \newcommand{\Sensitivity}{S} \newcommand{\basalRate}{b} \newcommand{\dampingCoefficient}{c} \newcommand{\mass}{m} \newcommand{\sensitivity}{s} \newcommand{\springScalar}{\kappa} \newcommand{\springVector}{\boldsymbol{ \kappa}} \newcommand{\springMatrix}{\boldsymbol{ \mathcal{K}}} \newcommand{\tfConcentration}{p} \newcommand{\tfDecayRate}{\delta} \newcommand{\tfMrnaConcentration}{f} \newcommand{\tfVector}{\mathbf{ \tfConcentration}} \newcommand{\velocity}{v} \newcommand{\sufficientStatsScalar}{g} \newcommand{\sufficientStatsVector}{\mathbf{ \sufficientStatsScalar}} \newcommand{\sufficientStatsMatrix}{\mathbf{G}} \newcommand{\switchScalar}{s} \newcommand{\switchVector}{\mathbf{ \switchScalar}} \newcommand{\switchMatrix}{\mathbf{S}} \newcommand{\tr}[1]{\text{tr}\left(#1\right)} \newcommand{\loneNorm}[1]{\left\Vert #1 \right\Vert_1} \newcommand{\ltwoNorm}[1]{\left\Vert #1 \right\Vert_2} \newcommand{\onenorm}[1]{\left\vert#1\right\vert_1} \newcommand{\twonorm}[1]{\left\Vert #1 \right\Vert} \newcommand{\vScalar}{v} \newcommand{\vVector}{\mathbf{v}} \newcommand{\vMatrix}{\mathbf{V}} \newcommand{\varianceDist}[2]{\text{var}_{#2}\left( #1 \right)} \newcommand{\vecb}[1]{\left(#1\right):} \newcommand{\weightScalar}{w} \newcommand{\weightVector}{\mathbf{ \weightScalar}} \newcommand{\weightMatrix}{\mathbf{W}} \newcommand{\weightedAdjacencyMatrix}{\mathbf{A}} \newcommand{\weightedAdjacencyScalar}{a} \newcommand{\weightedAdjacencyVector}{\mathbf{ \weightedAdjacencyScalar}} \newcommand{\onesVector}{\mathbf{1}} \newcommand{\zerosVector}{\mathbf{0}} $$
at Department of Computing Science, University of Glasgow on Feb 22, 2019 [reveal]
Neil D. Lawrence, University of Sheffield and Amazon Cambridge

Abstract

Machine learning solutions, in particular those based on deep learning methods, form an underpinning for the modern artificial intelligence revolution that has dominated popular press headlines and is having a strong influence on the wider tech agenda. In this talk I will give an overview of where we are now with machine learning solutions, and what challenges we face both in the near and far future. These include practical application of existing algorithms in the face of the need to explain decision making, mechanisms for improving the quality and availability of data, and dealing with large unstructured datasets.

$$\newcommand{\tk}[1]{} \newcommand{\Amatrix}{\mathbf{A}} \newcommand{\KL}[2]{\text{KL}\left( #1\,\|\,#2 \right)} \newcommand{\Kaast}{\kernelMatrix_{\mathbf{ \ast}\mathbf{ \ast}}} \newcommand{\Kastu}{\kernelMatrix_{\mathbf{ \ast} \inducingVector}} \newcommand{\Kff}{\kernelMatrix_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\Kfu}{\kernelMatrix_{\mappingFunctionVector \inducingVector}} \newcommand{\Kuast}{\kernelMatrix_{\inducingVector \bf\ast}} \newcommand{\Kuf}{\kernelMatrix_{\inducingVector \mappingFunctionVector}} \newcommand{\Kuu}{\kernelMatrix_{\inducingVector \inducingVector}} \newcommand{\Kuui}{\Kuu^{-1}} \newcommand{\Qaast}{\mathbf{Q}_{\bf \ast \ast}} \newcommand{\Qastf}{\mathbf{Q}_{\ast \mappingFunction}} \newcommand{\Qfast}{\mathbf{Q}_{\mappingFunctionVector \bf \ast}} \newcommand{\Qff}{\mathbf{Q}_{\mappingFunctionVector \mappingFunctionVector}} \newcommand{\aMatrix}{\mathbf{A}} \newcommand{\aScalar}{a} \newcommand{\aVector}{\mathbf{a}} \newcommand{\acceleration}{a} \newcommand{\bMatrix}{\mathbf{B}} \newcommand{\bScalar}{b} \newcommand{\bVector}{\mathbf{b}} \newcommand{\basisFunc}{\phi} \newcommand{\basisFuncVector}{\boldsymbol{ \basisFunc}} \newcommand{\basisFunction}{\phi} \newcommand{\basisLocation}{\mu} \newcommand{\basisMatrix}{\boldsymbol{ \Phi}} \newcommand{\basisScalar}{\basisFunction} \newcommand{\basisVector}{\boldsymbol{ \basisFunction}} \newcommand{\activationFunction}{\phi} \newcommand{\activationMatrix}{\boldsymbol{ \Phi}} \newcommand{\activationScalar}{\basisFunction} \newcommand{\activationVector}{\boldsymbol{ \basisFunction}} \newcommand{\bigO}{\mathcal{O}} \newcommand{\binomProb}{\pi} \newcommand{\cMatrix}{\mathbf{C}} \newcommand{\cbasisMatrix}{\hat{\boldsymbol{ \Phi}}} \newcommand{\cdataMatrix}{\hat{\dataMatrix}} \newcommand{\cdataScalar}{\hat{\dataScalar}} \newcommand{\cdataVector}{\hat{\dataVector}} \newcommand{\centeredKernelMatrix}{\mathbf{ \MakeUppercase{\centeredKernelScalar}}} \newcommand{\centeredKernelScalar}{b} \newcommand{\centeredKernelVector}{\centeredKernelScalar} \newcommand{\centeringMatrix}{\mathbf{H}} \newcommand{\chiSquaredDist}[2]{\chi_{#1}^{2}\left(#2\right)} \newcommand{\chiSquaredSamp}[1]{\chi_{#1}^{2}} \newcommand{\conditionalCovariance}{\boldsymbol{ \Sigma}} \newcommand{\coregionalizationMatrix}{\mathbf{B}} \newcommand{\coregionalizationScalar}{b} \newcommand{\coregionalizationVector}{\mathbf{ \coregionalizationScalar}} \newcommand{\covDist}[2]{\text{cov}_{#2}\left(#1\right)} \newcommand{\covSamp}[1]{\text{cov}\left(#1\right)} \newcommand{\covarianceScalar}{c} \newcommand{\covarianceVector}{\mathbf{ \covarianceScalar}} \newcommand{\covarianceMatrix}{\mathbf{C}} \newcommand{\covarianceMatrixTwo}{\boldsymbol{ \Sigma}} \newcommand{\croupierScalar}{s} \newcommand{\croupierVector}{\mathbf{ \croupierScalar}} \newcommand{\croupierMatrix}{\mathbf{ \MakeUppercase{\croupierScalar}}} \newcommand{\dataDim}{p} \newcommand{\dataIndex}{i} \newcommand{\dataIndexTwo}{j} \newcommand{\dataMatrix}{\mathbf{Y}} \newcommand{\dataScalar}{y} \newcommand{\dataSet}{\mathcal{D}} \newcommand{\dataStd}{\sigma} \newcommand{\dataVector}{\mathbf{ \dataScalar}} \newcommand{\decayRate}{d} \newcommand{\degreeMatrix}{\mathbf{ \MakeUppercase{\degreeScalar}}} \newcommand{\degreeScalar}{d} \newcommand{\degreeVector}{\mathbf{ \degreeScalar}} \newcommand{\diag}[1]{\text{diag}\left(#1\right)} \newcommand{\diagonalMatrix}{\mathbf{D}} \newcommand{\diff}[2]{\frac{\text{d}#1}{\text{d}#2}} \newcommand{\diffTwo}[2]{\frac{\text{d}^2#1}{\text{d}#2^2}} \newcommand{\displacement}{x} \newcommand{\displacementVector}{\textbf{\displacement}} \newcommand{\distanceMatrix}{\mathbf{ \MakeUppercase{\distanceScalar}}} \newcommand{\distanceScalar}{d} \newcommand{\distanceVector}{\mathbf{ \distanceScalar}} \newcommand{\eigenvaltwo}{\ell} \newcommand{\eigenvaltwoMatrix}{\mathbf{L}} \newcommand{\eigenvaltwoVector}{\mathbf{l}} \newcommand{\eigenvalue}{\lambda} \newcommand{\eigenvalueMatrix}{\boldsymbol{ \Lambda}} \newcommand{\eigenvalueVector}{\boldsymbol{ \lambda}} \newcommand{\eigenvector}{\mathbf{ \eigenvectorScalar}} \newcommand{\eigenvectorMatrix}{\mathbf{U}} \newcommand{\eigenvectorScalar}{u} \newcommand{\eigenvectwo}{\mathbf{v}} \newcommand{\eigenvectwoMatrix}{\mathbf{V}} \newcommand{\eigenvectwoScalar}{v} \newcommand{\entropy}[1]{\mathcal{H}\left(#1\right)} \newcommand{\errorFunction}{E} \newcommand{\expDist}[2]{\left\langle#1\right\rangle_{#2}} \newcommand{\expSamp}[1]{\left\langle#1\right\rangle} \newcommand{\expectation}[1]{\left\langle #1 \right\rangle } \newcommand{\expectationDist}[2]{\left\langle #1 \right\rangle _{#2}} \newcommand{\expectedDistanceMatrix}{\mathcal{D}} \newcommand{\eye}{\mathbf{I}} \newcommand{\fantasyDim}{r} \newcommand{\fantasyMatrix}{\mathbf{ \MakeUppercase{\fantasyScalar}}} \newcommand{\fantasyScalar}{z} \newcommand{\fantasyVector}{\mathbf{ \fantasyScalar}} \newcommand{\featureStd}{\varsigma} \newcommand{\gammaCdf}[3]{\mathcal{GAMMA CDF}\left(#1|#2,#3\right)} \newcommand{\gammaDist}[3]{\mathcal{G}\left(#1|#2,#3\right)} \newcommand{\gammaSamp}[2]{\mathcal{G}\left(#1,#2\right)} \newcommand{\gaussianDist}[3]{\mathcal{N}\left(#1|#2,#3\right)} \newcommand{\gaussianSamp}[2]{\mathcal{N}\left(#1,#2\right)} \newcommand{\uniformDist}[3]{\mathcal{U}\left(#1|#2,#3\right)} \newcommand{\uniformSamp}[2]{\mathcal{U}\left(#1,#2\right)} \newcommand{\given}{|} \newcommand{\half}{\frac{1}{2}} \newcommand{\heaviside}{H} \newcommand{\hiddenMatrix}{\mathbf{ \MakeUppercase{\hiddenScalar}}} \newcommand{\hiddenScalar}{h} \newcommand{\hiddenVector}{\mathbf{ \hiddenScalar}} \newcommand{\identityMatrix}{\eye} \newcommand{\inducingInputScalar}{z} \newcommand{\inducingInputVector}{\mathbf{ \inducingInputScalar}} \newcommand{\inducingInputMatrix}{\mathbf{Z}} \newcommand{\inducingScalar}{u} \newcommand{\inducingVector}{\mathbf{ \inducingScalar}} \newcommand{\inducingMatrix}{\mathbf{U}} \newcommand{\inlineDiff}[2]{\text{d}#1/\text{d}#2} \newcommand{\inputDim}{q} \newcommand{\inputMatrix}{\mathbf{X}} \newcommand{\inputScalar}{x} \newcommand{\inputSpace}{\mathcal{X}} \newcommand{\inputVals}{\inputVector} \newcommand{\inputVector}{\mathbf{ \inputScalar}} \newcommand{\iterNum}{k} \newcommand{\kernel}{\kernelScalar} \newcommand{\kernelMatrix}{\mathbf{K}} \newcommand{\kernelScalar}{k} \newcommand{\kernelVector}{\mathbf{ \kernelScalar}} \newcommand{\kff}{\kernelScalar_{\mappingFunction \mappingFunction}} \newcommand{\kfu}{\kernelVector_{\mappingFunction \inducingScalar}} \newcommand{\kuf}{\kernelVector_{\inducingScalar \mappingFunction}} \newcommand{\kuu}{\kernelVector_{\inducingScalar \inducingScalar}} \newcommand{\lagrangeMultiplier}{\lambda} \newcommand{\lagrangeMultiplierMatrix}{\boldsymbol{ \Lambda}} \newcommand{\lagrangian}{L} \newcommand{\laplacianFactor}{\mathbf{ \MakeUppercase{\laplacianFactorScalar}}} \newcommand{\laplacianFactorScalar}{m} \newcommand{\laplacianFactorVector}{\mathbf{ \laplacianFactorScalar}} \newcommand{\laplacianMatrix}{\mathbf{L}} \newcommand{\laplacianScalar}{\ell} \newcommand{\laplacianVector}{\mathbf{ \ell}} \newcommand{\latentDim}{q} \newcommand{\latentDistanceMatrix}{\boldsymbol{ \Delta}} \newcommand{\latentDistanceScalar}{\delta} \newcommand{\latentDistanceVector}{\boldsymbol{ \delta}} \newcommand{\latentForce}{f} \newcommand{\latentFunction}{u} \newcommand{\latentFunctionVector}{\mathbf{ \latentFunction}} \newcommand{\latentFunctionMatrix}{\mathbf{ \MakeUppercase{\latentFunction}}} \newcommand{\latentIndex}{j} \newcommand{\latentScalar}{z} \newcommand{\latentVector}{\mathbf{ \latentScalar}} \newcommand{\latentMatrix}{\mathbf{Z}} \newcommand{\learnRate}{\eta} \newcommand{\lengthScale}{\ell} \newcommand{\rbfWidth}{\ell} \newcommand{\likelihoodBound}{\mathcal{L}} \newcommand{\likelihoodFunction}{L} \newcommand{\locationScalar}{\mu} \newcommand{\locationVector}{\boldsymbol{ \locationScalar}} \newcommand{\locationMatrix}{\mathbf{M}} \newcommand{\variance}[1]{\text{var}\left( #1 \right)} \newcommand{\mappingFunction}{f} \newcommand{\mappingFunctionMatrix}{\mathbf{F}} \newcommand{\mappingFunctionTwo}{g} \newcommand{\mappingFunctionTwoMatrix}{\mathbf{G}} \newcommand{\mappingFunctionTwoVector}{\mathbf{ \mappingFunctionTwo}} \newcommand{\mappingFunctionVector}{\mathbf{ \mappingFunction}} \newcommand{\scaleScalar}{s} \newcommand{\mappingScalar}{w} \newcommand{\mappingVector}{\mathbf{ \mappingScalar}} \newcommand{\mappingMatrix}{\mathbf{W}} \newcommand{\mappingScalarTwo}{v} \newcommand{\mappingVectorTwo}{\mathbf{ \mappingScalarTwo}} \newcommand{\mappingMatrixTwo}{\mathbf{V}} \newcommand{\maxIters}{K} \newcommand{\meanMatrix}{\mathbf{M}} \newcommand{\meanScalar}{\mu} \newcommand{\meanTwoMatrix}{\mathbf{M}} \newcommand{\meanTwoScalar}{m} \newcommand{\meanTwoVector}{\mathbf{ \meanTwoScalar}} \newcommand{\meanVector}{\boldsymbol{ \meanScalar}} \newcommand{\mrnaConcentration}{m} \newcommand{\naturalFrequency}{\omega} \newcommand{\neighborhood}[1]{\mathcal{N}\left( #1 \right)} \newcommand{\neilurl}{http://inverseprobability.com/} \newcommand{\noiseMatrix}{\boldsymbol{ E}} \newcommand{\noiseScalar}{\epsilon} \newcommand{\noiseVector}{\boldsymbol{ \epsilon}} \newcommand{\noiseStd}{\sigma} \newcommand{\norm}[1]{\left\Vert #1 \right\Vert} \newcommand{\normalizedLaplacianMatrix}{\hat{\mathbf{L}}} \newcommand{\normalizedLaplacianScalar}{\hat{\ell}} \newcommand{\normalizedLaplacianVector}{\hat{\mathbf{ \ell}}} \newcommand{\numActive}{m} \newcommand{\numBasisFunc}{m} \newcommand{\numComponents}{m} \newcommand{\numComps}{K} \newcommand{\numData}{n} \newcommand{\numFeatures}{K} \newcommand{\numHidden}{h} \newcommand{\numInducing}{m} \newcommand{\numLayers}{\ell} \newcommand{\numNeighbors}{K} \newcommand{\numSequences}{s} \newcommand{\numSuccess}{s} \newcommand{\numTasks}{m} \newcommand{\numTime}{T} \newcommand{\numTrials}{S} \newcommand{\outputIndex}{j} \newcommand{\paramVector}{\boldsymbol{ \theta}} \newcommand{\parameterMatrix}{\boldsymbol{ \Theta}} \newcommand{\parameterScalar}{\theta} \newcommand{\parameterVector}{\boldsymbol{ \parameterScalar}} \newcommand{\partDiff}[2]{\frac{\partial#1}{\partial#2}} \newcommand{\precisionScalar}{j} \newcommand{\precisionVector}{\mathbf{ \precisionScalar}} \newcommand{\precisionMatrix}{\mathbf{J}} \newcommand{\pseudotargetScalar}{\widetilde{y}} \newcommand{\pseudotargetVector}{\mathbf{ \pseudotargetScalar}} \newcommand{\pseudotargetMatrix}{\mathbf{ \widetilde{Y}}} \newcommand{\rank}[1]{\text{rank}\left(#1\right)} \newcommand{\rayleighDist}[2]{\mathcal{R}\left(#1|#2\right)} \newcommand{\rayleighSamp}[1]{\mathcal{R}\left(#1\right)} \newcommand{\responsibility}{r} \newcommand{\rotationScalar}{r} \newcommand{\rotationVector}{\mathbf{ \rotationScalar}} \newcommand{\rotationMatrix}{\mathbf{R}} \newcommand{\sampleCovScalar}{s} \newcommand{\sampleCovVector}{\mathbf{ \sampleCovScalar}} \newcommand{\sampleCovMatrix}{\mathbf{s}} \newcommand{\scalarProduct}[2]{\left\langle{#1},{#2}\right\rangle} \newcommand{\sign}[1]{\text{sign}\left(#1\right)} \newcommand{\sigmoid}[1]{\sigma\left(#1\right)} \newcommand{\singularvalue}{\ell} \newcommand{\singularvalueMatrix}{\mathbf{L}} \newcommand{\singularvalueVector}{\mathbf{l}} \newcommand{\sorth}{\mathbf{u}} \newcommand{\spar}{\lambda} \newcommand{\trace}[1]{\text{tr}\left(#1\right)} \newcommand{\BasalRate}{B} \newcommand{\DampingCoefficient}{C} \newcommand{\DecayRate}{D} \newcommand{\Displacement}{X} \newcommand{\LatentForce}{F} \newcommand{\Mass}{M} \newcommand{\Sensitivity}{S} \newcommand{\basalRate}{b} \newcommand{\dampingCoefficient}{c} \newcommand{\mass}{m} \newcommand{\sensitivity}{s} \newcommand{\springScalar}{\kappa} \newcommand{\springVector}{\boldsymbol{ \kappa}} \newcommand{\springMatrix}{\boldsymbol{ \mathcal{K}}} \newcommand{\tfConcentration}{p} \newcommand{\tfDecayRate}{\delta} \newcommand{\tfMrnaConcentration}{f} \newcommand{\tfVector}{\mathbf{ \tfConcentration}} \newcommand{\velocity}{v} \newcommand{\sufficientStatsScalar}{g} \newcommand{\sufficientStatsVector}{\mathbf{ \sufficientStatsScalar}} \newcommand{\sufficientStatsMatrix}{\mathbf{G}} \newcommand{\switchScalar}{s} \newcommand{\switchVector}{\mathbf{ \switchScalar}} \newcommand{\switchMatrix}{\mathbf{S}} \newcommand{\tr}[1]{\text{tr}\left(#1\right)} \newcommand{\loneNorm}[1]{\left\Vert #1 \right\Vert_1} \newcommand{\ltwoNorm}[1]{\left\Vert #1 \right\Vert_2} \newcommand{\onenorm}[1]{\left\vert#1\right\vert_1} \newcommand{\twonorm}[1]{\left\Vert #1 \right\Vert} \newcommand{\vScalar}{v} \newcommand{\vVector}{\mathbf{v}} \newcommand{\vMatrix}{\mathbf{V}} \newcommand{\varianceDist}[2]{\text{var}_{#2}\left( #1 \right)} \newcommand{\vecb}[1]{\left(#1\right):} \newcommand{\weightScalar}{w} \newcommand{\weightVector}{\mathbf{ \weightScalar}} \newcommand{\weightMatrix}{\mathbf{W}} \newcommand{\weightedAdjacencyMatrix}{\mathbf{A}} \newcommand{\weightedAdjacencyScalar}{a} \newcommand{\weightedAdjacencyVector}{\mathbf{ \weightedAdjacencyScalar}} \newcommand{\onesVector}{\mathbf{1}} \newcommand{\zerosVector}{\mathbf{0}} $$

What is Machine Learning? [edit]

What is machine learning? At its most basic level machine learning is a combination of


$$\text{data} + \text{model} \xrightarrow{\text{compute}} \text{prediction}$$

where data is our observations. They can be actively or passively acquired (meta-data). The model contains our assumptions, based on previous experience. That experience can be other data, it can come from transfer learning, or it can merely be our beliefs about the regularities of the universe. In humans our models include our inductive biases. The prediction is an action to be taken or a categorization or a quality score. The reason that machine learning has become a mainstay of artificial intelligence is the importance of predictions in artificial intelligence. The data and the model are combined through computation.

In practice we normally perform machine learning using two functions. To combine data with a model we typically make use of:

a prediction function a function which is used to make the predictions. It includes our beliefs about the regularities of the universe, our assumptions about how the world works, e.g. smoothness, spatial similarities, temporal similarities.

an objective function a function which defines the cost of misprediction. Typically it includes knowledge about the world’s generating processes (probabilistic objectives) or the costs we pay for mispredictions (empiricial risk minimization).

The combination of data and model through the prediction function and the objectie function leads to a learning algorithm. The class of prediction functions and objective functions we can make use of is restricted by the algorithms they lead to. If the prediction function or the objective function are too complex, then it can be difficult to find an appropriate learning algorithm. Much of the acdemic field of machine learning is the quest for new learning algorithms that allow us to bring different types of models and data together.

A useful reference for state of the art in machine learning is the UK Royal Society Report, Machine Learning: Power and Promise of Computers that Learn by Example.

You can also check my post blog post on What is Machine Learning?..

Artificial Intelligence and Data Science [edit]

Machine learning technologies have been the driver of two related, but distinct disciplines. The first is data science. Data science is an emerging field that arises from the fact that we now collect so much data by happenstance, rather than by experimental design. Classical statistics is the science of drawing conclusions from data, and to do so statistical experiments are carefully designed. In the modern era we collect so much data that there’s a desire to draw inferences directly from the data.

As well as machine learning, the field of data science draws from statistics, cloud computing, data storage (e.g. streaming data), visualization and data mining.

In contrast, artificial intelligence technologies typically focus on emulating some form of human behaviour, such as understanding an image, or some speech, or translating text from one form to another. The recent advances in artifcial intelligence have come from machine learning providing the automation. But in contrast to data science, in artifcial intelligence the data is normally collected with the specific task in mind. In this sense it has strong relations to classical statistics.

Classically artificial intelligence worried more about logic and planning and focussed less on data driven decision making. Modern machine learning owes more to the field of Cybernetics (Wiener 1948) than artificial intelligence. Related fields include robotics, speech recognition, language understanding and computer vision.

There are strong overlaps between the fields, the wide availability of data by happenstance makes it easier to collect data for designing AI systems. These relations are coming through wide availability of sensing technologies that are interconnected by celluar networks, WiFi and the internet. This phenomenon is sometimes known as the Internet of Things, but this feels like a dangerous misnomer. We must never forget that we are interconnecting people, not things.

Convention for the Protection of Individuals with regard to Automatic Processing of Personal Data (1981/1/28)

Embodiment Factors [edit]

compute
 ≈ 100 gigaflops

 ≈ 16 petaflops
communicate
1 gigbit/s

100 bit/s
(compute/communicate)
104

1014

There is a fundamental limit placed on our intelligence based on our ability to communicate. Claude Shannon founded the field of information theory. The clever part of this theory is it allows us to separate our measurement of information from what the information pertains to1.

Shannon measured information in bits. One bit of information is the amount of information I pass to you when I give you the result of a coin toss. Shannon was also interested in the amount of information in the English language. He estimated that on average a word in the English language contains 12 bits of information.

Given typical speaking rates, that gives us an estimate of our ability to communicate of around 100 bits per second (Reed and Durlach 1998). Computers on the other hand can communicate much more rapidly. Current wired network speeds are around a billion bits per second, ten million times faster.

When it comes to compute though, our best estimates indicate our computers are slower. A typical modern computer can process make around 100 billion floating point operations per second, each floating point operation involves a 64 bit number. So the computer is processing around 6,400 billion bits per second.

It’s difficult to get similar estimates for humans, but by some estimates the amount of compute we would require to simulate a human brain is equivalent to that in the UK’s fastest computer (Ananthanarayanan et al. 2009), the MET office machine in Exeter, which in 2018 ranks as the 11th fastest computer in the world. That machine simulates the world’s weather each morning, and then simulates the world’s climate in the afternoon. It is a 16 petaflop machine, processing around 1,000 trillion bits per second.

Figure: The Lotus 49, view from the rear. The Lotus 49 was one of the last Formula One cars before the introduction of aerodynamic aids.

So when it comes to our ability to compute we are extraordinary, not compute in our conscious mind, but the underlying neuron firings that underpin both our consciousness, our subconsciousness as well as our motor control etc.

If we think of ourselves as vehicles, then we are massively overpowered. Our ability to generate derived information from raw fuel is extraordinary. Intellectually we have formula one engines.

But in terms of our ability to deploy that computation in actual use, to share the results of what we have inferred, we are very limited. So when you imagine the F1 car that represents a psyche, think of an F1 car with bicycle wheels.

Figure: Marcel Renault races a Renault 40 cv during the Paris-Madrid race, an early Grand Prix, in 1903. Marcel died later in the race after missing a warning flag for a sharp corner at Couhé Vérac, likely due to dust reducing visibility.

Just think of the control a driver would have to have to deploy such power through such a narrow channel of traction. That is the beauty and the skill of the human mind.

In contrast, our computers are more like go-karts. Underpowered, but with well-matched tires. They can communicate far more fluidly. They are more efficient, but somehow less extraordinary, less beautiful.

Figure: Caleb McDuff driving for WIX Silence Racing.

For humans, that means much of our computation should be dedicated to considering what we should compute. To do that efficiently we need to model the world around us. The most complex thing in the world around us is other humans. So it is no surprise that we model them. We second guess what their intentions are, and our communication is only necessary when they are departing from how we model them. Naturally, for this to work well, we need to understand those we work closely with. So it is no surprise that social communication, social bonding, forms so much of a part of our use of our limited bandwidth.

There is a second effect here, our need to anthropomorphise objects around us. Our tendency to model our fellow humans extends to when we interact with other entities in our environment. To our pets as well as inanimate objects around us, such as computers or even our cars. This tendency to over interpret could be a consequence of our limited ability to communicate.

For more details see this paper “Living Together: Mind and Machine Intelligence”, and this TEDx talk.

Evolved Relationship with Information [edit]

The high bandwidth of computers has resulted in a close relationship between the computer and data. Large amounts of information can flow between the two. The degree to which the computer is mediating our relationship with data means that we should consider it an intermediary.

Originaly our low bandwith relationship with data was affected by two characteristics. Firstly, our tendency to over-interpret driven by our need to extract as much knowledge from our low bandwidth information channel as possible. Secondly, by our improved understanding of the domain of mathematical statistics and how our cognitive biases can mislead us.

With this new set up there is a potential for assimilating far more information via the computer, but the computer can present this to us in various ways. If it’s motives are not aligned with ours then it can misrepresent the information. This needn’t be nefarious it can be simply as a result of the computer pursuing a different objective from us. For example, if the computer is aiming to maximize our interaction time that may be a different objective from ours which may be to summarize information in a representative manner in the shortest possible length of time.

For example, for me, it was a common experience to pick up my telephone with the intention of checking when my next appointment was, but to soon find myself distracted by another application on the phone, and end up reading something on the internet. By the time I’d finished reading, I would often have forgotten the reason I picked up my phone in the first place.

There are great benefits to be had from the huge amount of information we can unlock from this evolved relationship between us and data. In biology, large scale data sharing has been driven by a revolution in genomic, transcriptomic and epigenomic measurement. The improved inferences that that can be drawn through summarizing data by computer have fundamentally changed the nature of biological science, now this phenomenon is also infuencing us in our daily lives as data measured by happenstance is increasingly used to characterize us.

Better mediation of this flow actually requires a better understanding of human-computer interaction. This in turn involves understanding our own intelligence better, what its cognitive biases are and how these might mislead us.

For further thoughts see Guardian article on marketing in the internet era from 2015.

You can also check my blog post on System Zero..

Figure: The trinity of human, data and computer, and highlights the modern phenomenon. The communication channel between computer and data now has an extremely high bandwidth. The channel between human and computer and the channel between data and human is narrow. New direction of information flow, information is reaching us mediated by the computer.

What does Machine Learning do? [edit]

Any process of automation allows us to scale what we do by codifying a process in some way that makes it efficient and repeatable. Machine learning automates by emulating human (or other actions) found in data. Machine learning codifies in the form of a mathematical function that is learnt by a computer. If we can create these mathematical functions in ways in which they can interconnect, then we can also build systems.

Machine learning works through codifing a prediction of interest into a mathematical function. For example, we can try and predict the probability that a customer wants to by a jersey given knowledge of their age, and the latitude where they live. The technique known as logistic regression estimates the odds that someone will by a jumper as a linear weighted sum of the features of interest.


$$ \text{odds} = \frac{p(\text{bought})}{p(\text{not bought})} $$


log odds = β0 + β1age + β2latitude.
Here β0, β1 and β2 are the parameters of the model. If β1 and β2 are both positive, then the log-odds that someone will buy a jumper increase with increasing latitude and age, so the further north you are and the older you are the more likely you are to buy a jumper. The parameter β0 is an offset parameter, and gives the log-odds of buying a jumper at zero age and on the equator. It is likely to be negative2 indicating that the purchase is odds-against. This is actually a classical statistical model, and models like logistic regression are widely used to estimate probabilities from ad-click prediction to risk of disease.

This is called a generalized linear model, we can also think of it as estimating the probability of a purchase as a nonlinear function of the features (age, lattitude) and the parameters (the β values). The function is known as the sigmoid or logistic function, thus the name logistic regression.


$$ p(\text{bought}) = \sigmoid{\beta_0 + \beta_1 \text{age} + \beta_2 \text{latitude}}.$$
In the case where we have features to help us predict, we sometimes denote such features as a vector, $\inputVector$, and we then use an inner product between the features and the parameters, $\boldsymbol{\beta}^\top \inputVector = \beta_1 \inputScalar_1 + \beta_2 \inputScalar_2 + \beta_3 \inputScalar_3 ...$, to represent the argument of the sigmoid.


$$ p(\text{bought}) = \sigmoid{\boldsymbol{\beta}^\top \inputVector}.$$
More generally, we aim to predict some aspect of our data, $\dataScalar$, by relating it through a mathematical function, $\mappingFunction(\cdot)$, to the parameters, β and the data, $\inputVector$.


$$ \dataScalar = \mappingFunction\left(\inputVector, \boldsymbol{\beta}\right).$$
We call $\mappingFunction(\cdot)$ the prediction function.

To obtain the fit to data, we use a separate function called the objective function that gives us a mathematical representation of the difference between our predictions and the real data.


$$\errorFunction(\boldsymbol{\beta}, \dataMatrix, \inputMatrix)$$
A commonly used examples (for example in a regression problem) is least squares,
$$\errorFunction(\boldsymbol{\beta}, \dataMatrix, \inputMatrix) = \sum_{i=1}^\numData \left(\dataScalar_i - \mappingFunction(\inputVector_i, \boldsymbol{\beta})\right)^2.$$

If a linear prediction function is combined with the least squares objective function then that gives us a classical linear regression, another classical statistical model. Statistics often focusses on linear models because it makes interpretation of the model easier. Interpretation is key in statistics because the aim is normally to validate questions by analysis of data. Machine learning has typically focussed more on the prediction function itself and worried less about the interpretation of parameters, which are normally denoted by w instead of β. As a result non-linear functions are explored more often as they tend to improve quality of predictions but at the expense of interpretability.

Deep Learning [edit]

Classical statistical models and simple machine learning models have a great deal in common. The main difference between the fields is philosophical. Machine learning practitioners are typically more concerned with the quality of prediciton (e.g. measured by ROC curve) while statisticians tend to focus more on the interpretability of the model and the validity of any decisions drawn from that interpretation. For example, a statistical model may be used to validate whether a large scale intervention (such as the mass provision of mosquito nets) has had a long term effect on disease (such as malaria). In this case one of the covariates is likely to be the provision level of nets in a particular region. The response variable would be the rate of malaria disease in the region. The parmaeter, β1 associated with that covariate will demonstrate a positive or negative effect which would be validated in answering the question. The focus in statistics would be less on the accuracy of the response variable and more on the validity of the interpretation of the effect variable, β1.

A machine learning practitioner on the other hand would typically denote the parameter w1, instead of β1 and would only be interested in the output of the prediction function, $\mappingFunction(\cdot)$ rather than the parameter itself. The general formalism of the prediction function allows for non-linear models. In machine learning, the emphasis on prediction over interpretability means that non-linear models are often used. The parameters, w, are a means to an end (good prediction) rather than an end in themselves (interpretable).

DeepFace [edit]

Figure: The DeepFace architecture (Taigman et al. 2014), visualized through colors to represent the functional mappings at each layer. There are 120 million parameters in the model.

The DeepFace architecture (Taigman et al. 2014) consists of layers that deal with translation and rotational invariances. These layers are followed by three locally-connected layers and two fully-connected layers. Color illustrates feature maps produced at each layer. The neural network includes more than 120 million parameters, where more than 95% come from the local and fully connected layers.

Deep Learning as Pinball [edit]

Figure: Deep learning models are composition of simple functions. We can think of a pinball machine as an analogy. Each layer of pins corresponds to one of the layers of functions in the model. Input data is represented by the location of the ball from left to right when it is dropped in from the top. Output class comes from the position of the ball as it leaves the pins at the bottom.

Sometimes deep learning models are described as being like the brain, or too complex to understand, but one analogy I find useful to help the gist of these models is to think of them as being similar to early pin ball machines.

In a deep neural network, we input a number (or numbers), whereas in pinball, we input a ball.

Think of the location of the ball on the left-right axis as a single number. Our simple pinball machine can only take one number at a time. As the ball falls through the machine, each layer of pins can be thought of as a different layer of ‘neurons’. Each layer acts to move the ball from left to right.

In a pinball machine, when the ball gets to the bottom it might fall into a hole defining a score, in a neural network, that is equivalent to the decision: a classification of the input object.

An image has more than one number associated with it, so it is like playing pinball in a hyper-space.

Figure: At initialization, the pins, which represent the parameters of the function, aren’t in the right place to bring the balls to the correct decisions.

Figure: After learning the pins are now in the right place to bring the balls to the correct decisions.

Learning involves moving all the pins to be in the correct position, so that the ball ends up in the right place when it’s fallen through the machine. But moving all these pins in hyperspace can be difficult.

In a hyper-space you have to put a lot of data through the machine for to explore the positions of all the pins. Even when you feed many millions of data points through the machine, there are likely to be regions in the hyper-space where no ball has passed. When future test data passes through the machine in a new route unusual things can happen.

Adversarial examples exploit this high dimensional space. If you have access to the pinball machine, you can use gradient methods to find a position for the ball in the hyper space where the image looks like one thing, but will be classified as another.

Probabilistic methods explore more of the space by considering a range of possible paths for the ball through the machine. This helps to make them more data efficient and gives some robustness to adversarial examples.

Bayesian Inference by Rejection Sampling [edit]

One view of Bayesian inference is to assume we are given a mechanism for generating samples, where we assume that mechanism is representing on accurate view on the way we believe the world works.

This mechanism is known as our prior belief.

We combine our prior belief with our observations of the real world by discarding all those samples that are inconsistent with our prior. The likelihood defines mathematically what we mean by inconsistent with the prior. The higher the noise level in the likelihood, the looser the notion of consistent.

The samples that remain are considered to be samples from the posterior.

This approach to Bayesian inference is closely related to two sampling techniques known as rejection sampling and importance sampling. It is realized in practice in an approach known as approximate Bayesian computation (ABC) or likelihood-free inference.

In practice, the algorithm is often too slow to be practical, because most samples will be inconsistent with the data and as a result the mechanism has to be operated many times to obtain a few posterior samples.

However, in the Gaussian process case, when the likelihood also assumes Gaussian noise, we can operate this mechanism mathematically, and obtain the posterior density analytically. This is the benefit of Gaussian processes.

Figure: One view of Bayesian inference is we have a machine for generating samples (the prior), and we discard all samples inconsistent with our data, leaving the samples of interest (the posterior). The Gaussian process allows us to do this analytically.

Olympic Marathon Data [edit]

  • Gold medal times for Olympic Marathon since 1896.
  • Marathons before 1924 didn’t have a standardised distance.
  • Present results using pace per km.
  • In 1904 Marathon was badly organised leading to very slow times.
Image from Wikimedia Commons http://bit.ly/16kMKHQ

The first thing we will do is load a standard data set for regression modelling. The data consists of the pace of Olympic Gold Medal Marathon winners for the Olympics from 1896 to present. First we load in the data and plot.

Figure: Olympic marathon pace times since 1892.

Things to notice about the data include the outlier in 1904, in this year, the olympics was in St Louis, USA. Organizational problems and challenges with dust kicked up by the cars following the race meant that participants got lost, and only very few participants completed.

More recent years see more consistently quick marathons.

Alan Turing [edit]

Figure: Alan Turing, in 1946 he was only 11 minutes slower than the winner of the 1948 games. Would he have won a hypothetical games held in 1946? Source: Alan Turing Internet Scrapbook.

If we had to summarise the objectives of machine learning in one word, a very good candidate for that word would be generalization. What is generalization? From a human perspective it might be summarised as the ability to take lessons learned in one domain and apply them to another domain. If we accept the definition given in the first session for machine learning,
$$ \text{data} + \text{model} \xrightarrow{\text{compute}} \text{prediction} $$
then we see that without a model we can’t generalise: we only have data. Data is fine for answering very specific questions, like “Who won the Olympic Marathon in 2012?”, because we have that answer stored, however, we are not given the answer to many other questions. For example, Alan Turing was a formidable marathon runner, in 1946 he ran a time 2 hours 46 minutes (just under four minutes per kilometer, faster than I and most of the other Endcliffe Park Run runners can do 5 km). What is the probability he would have won an Olympics if one had been held in 1946?

To answer this question we need to generalize, but before we formalize the concept of generalization let’s introduce some formal representation of what it means to generalize in machine learning.

Our first objective will be to perform a Gaussian process fit to the data, we’ll do this using the GPy software.

The first command sets up the model, then m_full.optimize() optimizes the parameters of the covariance function and the noise level of the model. Once the fit is complete, we’ll try creating some test points, and computing the output of the GP model in terms of the mean and standard deviation of the posterior functions between 1870 and 2030. We plot the mean function and the standard deviation at 200 locations. We can obtain the predictions using y_mean, y_var = m_full.predict(xt)

Now we plot the results using the helper function in teaching_plots.

Figure: Gaussian process fit to the Olympic Marathon data. The error bars are too large, perhaps due to the outlier from 1904.

Fit Quality

In the fit we see that the error bars (coming mainly from the noise variance) are quite large. This is likely due to the outlier point in 1904, ignoring that point we can see that a tighter fit is obtained. To see this making a version of the model, m_clean, where that point is removed.

x_clean=np.vstack((x[0:2, :], x[3:, :]))
y_clean=np.vstack((y[0:2, :], y[3:, :]))

m_clean = GPy.models.GPRegression(x_clean,y_clean)
_ = m_clean.optimize()

Deep GP Fit [edit]

Let’s see if a deep Gaussian process can help here. We will construct a deep Gaussian process with one hidden layer (i.e. one Gaussian process feeding into another).

Build a Deep GP with an additional hidden layer (one dimensional) to fit the model.

Now optimize the model.

Olympic Marathon Data Deep GP

Figure: Deep GP fit to the Olympic marathon data. Error bars now change as the prediction evolves.

Olympic Marathon Data Deep GP

Figure: Point samples run through the deep Gaussian process show the distribution of output locations.

Fitted GP for each layer

Now we explore the GPs the model has used to fit each layer. First of all, we look at the hidden layer.

Figure: The mapping from input to the latent layer is broadly, with some flattening as time goes on. Variance is high across the input range.

Figure: The mapping from the latent layer to the output layer.

Olympic Marathon Pinball Plot

Figure: A pinball plot shows the movement of the ‘ball’ as it passes through each layer of the Gaussian processes. Mean directions of movement are shown by lines. Shading gives one standard deviation of movement position. At each layer, the uncertainty is reset. The overal uncertainty is the cumulative uncertainty from all the layers. There is some grouping of later points towards the right in the first layer, which also injects a large amount of uncertainty. Due to flattening of the curve in the second layer towards the right the uncertainty is reduced in final output.

The pinball plot shows the flow of any input ball through the deep Gaussian process. In a pinball plot a series of vertical parallel lines would indicate a purely linear function. For the olypmic marathon data we can see the first layer begins to shift from input towards the right. Note it also does so with some uncertainty (indicated by the shaded backgrounds). The second layer has less uncertainty, but bunches the inputs more strongly to the right. This input layer of uncertainty, followed by a layer that pushes inputs to the right is what gives the heteroschedastic noise.

Supply Chain [edit]

Figure: Packhorse Bridge under Burbage Edge. This packhorse route climbs steeply out of Hathersage and heads towards Sheffield. Packhorses were the main route for transporting goods across the Peak District. The high cost of transport is one driver of the ‘smith’ model, where there is a local skilled person responsible for assembling or creating goods (e.g. a blacksmith).

On Sunday mornings in Sheffield, I often used to run across Packhorse Bridge in Burbage valley. The bridge is part of an ancient network of trails crossing the Pennines that, before Turnpike roads arrived in the 18th century, was the main way in which goods were moved. Given that the moors around Sheffield were home to sand quarries, tin mines, lead mines and the villages in the Derwent valley were known for nail and pin manufacture, this wasn’t simply movement of agricultural goods, but it was the infrastructure for industrial transport.

The profession of leading the horses was known as a Jagger and leading out of the village of Hathersage is Jagger’s Lane, a trail that headed underneath Stanage Edge and into Sheffield.

The movement of goods from regions of supply to areas of demand is fundamental to our society. The physical infrastructure of supply chain has evolved a great deal over the last 300 years.

Cromford [edit]

Figure: Richard Arkwright is regarded of the founder of the modern factory system. Factories exploit distribution networks to centralize production of goods. Arkwright located his factory in Cromford due to proximity to Nottingham Weavers (his market) and availability of water power from the tributaries of the Derwent river. When he first arrived there was almost no transportation network. Over the following 200 years The Cromford Canal (1790s), a Turnpike (now the A6, 1816-18) and the High Peak Railway (now closed, 1820s) were all constructed to improve transportation access as the factory blossomed.

Richard Arkwright is known as the father of the modern factory system. In 1771 he set up a Mill for spinning cotton yarn in the village of Cromford, in the Derwent Valley. The Derwent valley is relatively inaccessible. Raw cotton arrived in Liverpool from the US and India. It needed to be transported on packhorse across the bridleways of the Pennines. But Cromford was a good location due to proximity to Nottingham, where weavers where consuming the finished thread, and the availability of water power from small tributaries of the Derwent river for Arkwright’s water frames which automated the production of yarn from raw cotton.

By 1794 the Cromford Canal was opened to bring coal in to Cromford and give better transport to Nottingham. The construction of the canals was driven by the need to improve the transport infrastructure, facilitating the movement of goods across the UK. Canals, roads and railways were initially constructed by the economic need for moving goods. To improve supply chain.

The A6 now does pass through Cromford, but at the time he moved there there was merely a track. The High Peak Railway was opened in 1832, it is now converted to the High Peak Trail, but it remains the highest railway built in Britain.

Cooper (1991)

Containerization [edit]

Figure: The container is one of the major drivers of globalization, and arguably the largest agent of social change in the last 100 years. It reduces the cost of transportation, significantly changing the appropriate topology of distribution networks. The container makes it possible to ship goods halfway around the world for cheaper than it costs to process those goods, leading to an extended distribution topology.

Containerization has had a dramatic effect on global economics, placing many people in the developing world at the end of the supply chain.

Figure: Wild Alaskan Cod, being solid in the Pacific Northwest, that is a product of China. It is cheaper to ship the deep frozen fish thousands of kilometers for processing than to process locally.

For example, you can buy Wild Alaskan Cod fished from Alaska, processed in China, sold in North America. This is driven by the low cost of transport for frozen cod vs the higher relative cost of cod processing in the US versus China. Similarly, Scottish prawns are also processed in China for sale in the UK.

This effect on cost of transport vs cost of processing is the main driver of the topology of the modern supply chain and the associated effect of globalization. If transport is much cheaper than processing, then processing will tend to agglomerate in places where processing costs can be minimized.

Large scale global economic change has principally been driven by changes in the technology that drives supply chain.

Supply chain is a large-scale automated decision making network. Our aim is to make decisions not only based on our models of customer behavior (as observed through data), but also by accounting for the structure of our fulfilment center, and delivery network.

Many of the most important questions in supply chain take the form of counterfactuals. E.g. “What would happen if we opened a manufacturing facility in Cambridge?” A counter factual is a question that implies a mechanistic understanding of a system. It goes beyond simple smoothness assumptions or translation invariants. It requires a physical, or mechanistic understanding of the supply chain network. For this reason, the type of models we deploy in supply chain often involve simulations or more mechanistic understanding of the network.

In supply chain Machine Learning alone is not enough, we need to bridge between models that contain real mechanisms and models that are entirely data driven.

This is challenging, because as we introduce more mechanism to the models we use, it becomes harder to develop efficient algorithms to match those models to data.

Deploying Artificial Intelligence [edit]

With the wide availability of new techniques, we are currently creating Artifical Intelligence through combination of machine learning algorithms to form machine learning systems.

This effect is amplified through the growth in sensorics, in particular the movement of cloud computing towards the customer. The barrier between cloud and device is blurring. This phenomenon is sometimes known as fog computing, or computing on the edge.

This presents major new challenges for machine learning systems design. We would like an internet of intelligence but currently our AI systems are fragile. A classical systems approach to design does not handle evolving environments well.

Machine Learning Systems Design [edit]

The challenges of integrating different machine learning components into a whole that acts effectively as a system seem unresolved. In software engineering, separating parts of a system in this way is known as component-based software engineering. The core idea is that the different parts of the system can be independently designed according to a sub-specfication. This is sometimes known as separation of concerns. However, once the components are machine learning based, tighter coupling becomes a side effect of the learned nature of the system. For example if a driverless car’s detection of cyclist is dependent on its detection of the road surface, a change in the road surface detection algorithm will have downstream effects on the cyclist detection. Even if the road detection system has been improved by objective measures, the cyclist detection system may have become sensitive to the foibles of the previous version of road detection and will need to be retrained.

Most of our experience with deployment relies on some approximation to the component based model, this is also important for verification of the system. If the components of the system can be verified then the composed system can also, potentially, be verified.

Pigeonholing [edit]

Figure: Decompartmentalization of the model into parts can be seen as pigeonholing the separate tasks that are required.

To deal with the complexity of systems design, a common approach is to break complex systems down into a series of tasks. An approach we can think of as “pigeonholing”. Classically, a sub-task could be thought of as a particular stage in machining (by analogy to productionlines in factories) or a sub-routine call in computing. Machine learning allows any complex sub-task, that was difficult to decompose by classical methods, to be reconstituted by acquiring data. In particular, when we think of emulating a human, we can ask many humans to perform the sub-task many times and fit machine learning models to reconstruct the performance, or to emulate the human in the performance of the task. For example, the decomposition of a complex process such as driving a car into apparently obvious sub-tasks (following the road, identifying pedestrians, etc).

The practitioner’s approach to deploying artificial intelligence systems is to build up systems of machine learning components. To build a machine learning system, we decompose the task into parts, each of which we can emulate with ML methods. These parts are typically independently constructed and verified. For example, in a driverless car we can decompose the tasks into components such as “pedestrian detection” and “road line detection”. Each of these components can be constructed with, for example, a classification algorithm. Nowadays, people will often deploy a deep neural network, but for many tasks a random forest algorithm may be sufficient. We can then superimpose a logic on top. For example, “Follow the road line unless you detect a pedestrian in the road”.

This allows for verification of car performance, as long as we can verify the individual components. However, it also implies that the AI systems we deploy are fragile.

Our intelligent systems are composed by “pigeonholing” each indvidual task, then substituting with a machine learning model.

But this is not a robust approach to systems design. The definition of sub-tasks can lead to a single point of failure, where if any sub-task fails, the entire system fails.

Rapid Reimplementation

This is also the classical approach to automation, but in traditional automation we also ensure the environment in which the system operates becomes controlled. For example, trains run on railway lines, fast cars run on motorways, goods are manufactured in a controlled factory environment.

The difference with modern automated decision making systems is our intention is to deploy them in the uncontrolled environment that makes up our own world.

This exposes us to either unforseen circumstances or adversarial action. And yet it is unclear our our intelligent systems are capable of adapting to this.

We become exposed to mischief and adversaries. Adversaries intentially may wish to take over the artificial intelligence system, and mischief is the constant practice of many in our society. Simply watching a 10 year old interact with a voice agent such as Alexa or Siri shows that they are delighted when the can make the the “intelligent” agent seem foolish.

The Centrifugal Governor [edit]

Figure: Centrifugal governor as held by “Science” on Holborn Viaduct

Boulton and Watt’s Steam Engine [edit]

Figure: Watt’s Steam Engine which made Steam Power Efficient and Practical.

James Watt’s steam engine contained an early machine learning device. In the same way that modern systems are component based, his engine was composed of components. One of which is a speed regulator sometimes known as Watt’s governor. The two balls in the center of the image, when spun fast, rise, and through a linkage mechanism.

The centrifugal governor was made famous by Boulton and Watt when it was deployed in the steam engine. Studying stability in the governor is the main subject of James Clerk Maxwell’s paper on the theoretical analysis of governors (Maxwell 1867). This paper is a founding paper of control theory. In an acknowledgment of its influence, Wiener used the name cybernetics to describe the field of control and communication in animals and the machine (Wiener 1948). Cybernetics is the Greek word for governor, which comes from the latin for helmsman.

A governor is one of the simplest artificial intelligence systems. It senses the speed of an engine, and acts to change the position of the valve on the engine to slow it down.

Although it’s a mechanical system a governor can be seen as automating a role that a human would have traditionally played. It is an early example of artificial intelligence.

The centrifugal governor has several parameters, the weight of the balls used, the length of the linkages and the limits on the balls movement.

Two principle differences exist between the centrifugal governor and artificial intelligence systems of today.

  1. The centrifugal governor is a physical system and it is an integral part of a wider physical system that it regulates (the engine).
  2. The parameters of the governor were set by hand, our modern artificial intelligence systems have their parameters set by data.

Figure: The centrifugal governor, an early example of a decision making system. The parameters of the governor include the lengths of the linkages (which effect how far the throttle opens in response to movement in the balls), the weight of the balls (which effects inertia) and the limits of to which the balls can rise.

This has the basic components of sense and act that we expect in an intelligent system, and this system saved the need for a human operator to manually adjust the system in the case of overspeed. Overspeed has the potential to destroy an engine, so the governor operates as a safety device.

The first wave of automation did bring about sabotoage as a worker’s response. But if machinery was sabotaged, for example, if the linkage between sensor (the spinning balls) and action (the valve closure) was broken, this would be obvious to the engine operator at start up time. The machine could be repaired before operation.

The centrifugal governor was a key component in the Boulton-Watt steam engine. It senses increases in speed in the engine and closed the steam valve to prevent the engine overspeeding and destroying itself. Until the invention of this device, it was a human job to do this.

The formal study of governors and other feedback control devices was then began by James Clerk Maxwell, the Scottish physicist. This field became the foundation of our modern techniques of artificial intelligence through Norbert Wiener’s book Cybernetics (Wiener 1948). Cybernetics is Greek for governor, a word that in itself simply means helmsman in English.

The recent WannaCry virus that had a wide impact on our health services ecosystem was exploiting a security flaw in Windows systems that was first exploited by a virus called Stuxnet.

Stuxnet was a virus designed to infect the Iranian nuclear program’s Uranium enrichment centrifuges. A centrifuge is prevented from overspeed by a controller, just like the centrifugal governor. Only now it is implemented in control logic, in this case on a Siemens PLC controller.

Stuxnet infected these controllers and took over the response signal in the centrifuge, fooling the system into thinking that no overspeed was occuring. As a result, the centrifuges destroyed themselves through spinning too fast.

This is equivalent to detaching the governor from the steam engine. Such sabotage would be easily recognized by a steam engine operator. The challenge for the operators of the Iranian Uranium centrifuges was that the sabotage was occurring inside the electronics.

That is the effect of an adversary on an intelligent system, but even without adveraries, the mischief of a 10 year old can confuse our AIs.

Peppercorns [edit]

Figure: A peppercorn is a system design failure which is not a bug, but a conformance to design specification that causes problems when the system is deployed in the real world with mischevious and adversarial actors.

Asking Siri “What is a trillion to the power of a thousand minus one?” leads to a 30 minute response3 consisting of only 9s. I found this out because my nine year old grabbed my phone and did it. The only way to stop Siri was to force closure. This is an interesting example of a system feature that’s not a bug, in fact it requires clever processing from Wolfram Alpha. But it’s an unexpected result from the system performing correctly.

This challenge of facing a circumstance that was unenvisaged in design but has consequences in deployment becomes far larger when the environment is uncontrolled. Or in the extreme case, where actions of the intelligent system effect the wider environment and change it.

These unforseen circumstances are likely to lead to need for much more efficient turn-around and update for our intelligent systems. Whether we are correcting for security flaws (which are bugs) or unenvisaged circumstantial challenges: an issue I’m referring to as peppercorns. Rapid deployment of system updates is required. For example, Apple have “fixed” the problem of Siri returning long numbers.

The challenge is particularly acute because of the scale at which we can deploy AI solutions. This means when something does go wrong, it may be going wrong in billions of households simultaneously.

You can also check this blog post on Decision Making and Diversity. and this blog post on Natural vs Artifical Intelligence..

Emukit [edit]

Figure: The Emukit software is a set of software tools for emulation and surrogate modeling. https://amzn.github.io/emukit/

The aim is to provide a suite where different approaches to emulation are assimilated under one roof. The current version of Emukit includes multi-fidelity emulation for build surrogate models when data is obtained from multiple information sources that have different fidelity and/or cost; Bayesian optimisation for optimising physical experiments and tune parameters of machine learning algorithms or other computational simulations; experimental design and active learning: design the most informative experiments and perform active learning with machine learning models; sensitivity analysis: analyse the influence of inputs on the outputs of a given system; and Bayesian quadrature: efficiently compute the integrals of functions that are expensive to evaluate.

Conclusion [edit]

Artificial intelligence and data science are fundamentally different. In one you are dealing with data collecte by happenstance, in the other you are trying to build systems in the real world, often by actively collecting data. Our approaches to systems design are building powerful machines that will be deployed in evolving environments. But this is presenting key challenges in how we maintain and manage our machine learning systems.

References

Ananthanarayanan, Rajagopal, Steven K. Esser, Horst D. Simon, and Dharmendra S. Modha. 2009. “The Cat Is Out of the Bag: Cortical Simulations with 109 Neurons, 1013 Synapses.” In Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis - Sc ’09. https://doi.org/10.1145/1654059.1654124.

Cooper, Brian. 1991. Transformation of a Valley: Derbyshire Derwent. Scarthin Books.

Maxwell, James Clerk. 1867. “On Governors.” Proceedings of the Royal Society of London 16. The Royal Society: 270–83. http://www.jstor.org/stable/112510.

Reed, Charlotte, and Nathaniel I. Durlach. 1998. “Note on Information Transfer Rates in Human Communication.” Presence Teleoperators & Virtual Environments 7 (5): 509–18. https://doi.org/10.1162/105474698565893.

Taigman, Yaniv, Ming Yang, Marc’Aurelio Ranzato, and Lior Wolf. 2014. “DeepFace: Closing the Gap to Human-Level Performance in Face Verification.” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR.2014.220.

Wiener, Norbert. 1948. Cybernetics: Control and Communication in the Animal and the Machine. Cambridge, MA: MIT Press.


  1. the challenge of understanding what information pertains to is known as knowledge representation.

  2. The logarithm of a number less than one is negative, for a number greater than one the logarithm is positive. So if odds are greater than evens (odds-on) the log-odds are positive, if the odds are less than evens (odds-against) the log-odds will be negative.

  3. Apple has fixed this issue so that Siri no longer does this.