Machine Learning and the Physical World

Neil D. Lawrence

Tuebingen ML in Science Conference

Laplace’s Demon

Laplace’s Demon

Philosophical Essay on Probabilities Laplace (1814) pg 3

Machine Learning

\[ \text{model} + \text{data} \stackrel{\text{compute}}{\rightarrow} \text{prediction}\]

Theory of Everything

If we do discover a theory of everything … it would be the ultimate triumph of human reason-for then we would truly know the mind of God

Stephen Hawking in A Brief History of Time 1988

Emergent Behaviour

Loneliness
loneliness

Crowding
overcrowding

Birth
birth

Glider

Glider (1969)

Loafer

Loafer (2013)

Laplace’s Gremlin

Philosophical Essay on Probabilities Laplace (1814) pg 5

Figure: Science on Holborn Viaduct, cradling the Centrifugal Governor.

On Governors, James Clerk Maxwell 1868

Boulton and Watt’s Lap Engine

Lap Engine (1788)
total energy
=
available energy
+
temperature
\(\times\)
entropy

The Gap

  • There is a gap between the world of data science and AI.
  • The mapping of the virtual onto the physical world.
  • E.g. Causal understanding.

Statistical Emulation

Emulation

Emulation

Emulation

Emulation

Emulation

Prime Air

Gur Kimchi Paul Viola David Moro

Buying System

Monolithic System

Service Oriented Architecture

Intellectual Debt

Technical Debt

  • Compare with technical debt.
  • Highlighted by Sculley et al. (2015).

Separation of Concerns

Intellectual Debt

  • Technical debt is the inability to maintain your complex software system.

  • Intellectual debt is the inability to explain your software system.

Auto AI

  • Auto ML is great but not sufficient
  • Interacting components in an ML system
  • Identify problems, and automatically deploy solutions

Deep Emulation

Deep Emulation

Deep Emulation

Deep Emulation

The Accelerate Programme

  • Research
  • Teaching and learning
    • Ramp or Bridge model
  • Engagement

ML and the Physical World Course

Thanks!

References

Laplace, P.S., 1814. Essai philosophique sur les probabilités, 2nd ed. Courcier, Paris.
Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.-F., Dennison, D., 2015. Hidden technical debt in machine learning systems, in: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (Eds.), Advances in Neural Information Processing Systems 28. Curran Associates, Inc., pp. 2503–2511.