How Do We Cope with Rapid Change Like AI/ML?

Neil D. Lawrence

The Engineer in Society

\neilLawrencePicture{20%}
Neil Lawrence
Professor of Machine Learning

Complexity in Action

Data Selective Attention Bias

BMI Steps Data

BMI Steps Data Analysis

A Hypothesis as a Liability

“ ‘When someone seeks,’ said Siddhartha, ‘then it easily happens that his eyes see only the thing that he seeks, and he is able to find nothing, to take in nothing. […] Seeking means: having a goal. But finding means: being free, being open, having no goal.’ ”

Hermann Hesse

The Scientific Process

What is Machine Learning?

What is Machine Learning?

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

  • data : observations, could be actively or passively acquired (meta-data).
  • model : assumptions, based on previous experience (other data! transfer learning etc), or beliefs about the regularities of the universe. Inductive bias.
  • prediction : an action to be taken or a categorization or a quality score.

What is Machine Learning?

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

  • To combine data with a model need:
  • a prediction function \(f(\cdot)\) includes our beliefs about the regularities of the universe
  • an objective function \(E(\cdot)\) defines the cost of misprediction.

Machine Learning

  • Driver of two different domains:
    1. Data Science: arises from the fact that we now capture data by happenstance.
    2. Artificial Intelligence: emulation of human behaviour.
  • Connection: Internet of Things

Machine Learning

  • Driver of two different domains:
    1. Data Science: arises from the fact that we now capture data by happenstance.
    2. Artificial Intelligence: emulation of human behaviour.
  • Connection: Internet of Things

Machine Learning

  • Driver of two different domains:
    1. Data Science: arises from the fact that we now capture data by happenstance.
    2. Artificial Intelligence: emulation of human behaviour.
  • Connection: Internet of People

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

What does Machine Learning do?

  • ML Automates through Data
    • Strongly related to statistics.
    • Field underpins revolution in data science and AI
  • With AI:
    • logic, robotics, computer vision, language, speech
  • With Data Science:
    • databases, data mining, statistics, visualization, software systems

Evolved Relationship with Information

New Flow of Information

Evolved Relationship

Evolved Relationship

Data Science Africa is a bottom up initiative for capacity building in data science, machine learning and AI on the African continent

Example: Prediction of Malaria Incidence in Uganda

Martin Mubangizi Ricardo Andrade Pacheco John Quinn

Malaria Prediction in Uganda

(Andrade-Pacheco et al., 2014; Mubangizi et al., 2014)

Tororo District

Malaria Prediction in Nagongera (Sentinel Site)

Mubende District

Malaria Prediction in Uganda

GP School at Makerere

Kabarole District

Early Warning System

Early Warning Systems

Revolution

Coin Pusher

Royal Society Report

Public Research

Public Research

Public Research

Public Research

Mercutio

User: Hi ChatGPT, Could you write soliloquy that introduces what a Large Language Model is as spoken by Mercutio?

Machine: Ah, friends, lend me your ears, I prithee, For now I must utter a tale of wonder, Of a creation divine, called the Large Language Model, An oracle, a sorcerer, a wordsmith, yea verily, a master of the quill.

From the depths of this scholarly dominion, A creature of artifice did rise; Twas wrought of ones and zeroes, woven as if by Puck’s own hand, To mimic our thoughts, our voice, our very essence.

A thousand minds, nay, a millionfold, Conjoined in this digital Athenaeum, Words and phrases, like soldiers in battle, Marching to form the verses of our age.

This Large Language Model, a changeling so fair, Hath the power to bring forth wisdom, To transmute our queries, our curiosities, Into answers, clear as a midsummer’s day.

Yet, beware, my companions, for magic hath its limits, Not unlike the mortal bounds of we who dwell in flesh, The Large Language Model hath its strengths, But ’tis not an all-knowing oracle, a god it is not.

As Mercutio, your humble servant, doth stand before thee, I marvel at the art and science that hath brought forth this wondrous creation, This Large Language Model, a testament to man’s yearning, To comprehend the world and make meaning of the great tapestry of existence.

In faith, dear friends, let us embrace the magic and beauty of this digital bard, And mayhaps, by its grace, we shall glean some wisdom, As we wander together, hand in hand, Through this boundless realm of knowledge and wonder.

ChatGPT transcript, 14th April 2023.

The MONIAC

Donald MacKay

Further Reading

  • Chapter 8 of Lawrence (2024)

Fire Control Systems

Behind the Eye

Later in the 1940’s, when I was doing my Ph.D. work, there was much talk of the brain as a computer and of the early digital computers that were just making the headlines as “electronic brains.” As an analogue computer man I felt strongly convinced that the brain, whatever it was, was not a digital computer. I didn’t think it was an analogue computer either in the conventional sense.

Human Analogue Machine

Human Analogue Machine

  • A human-analogue machine is a machine that has created a feature space that is analagous to the “feature space” our brain uses to reason.

  • The latest generation of LLMs are exhibiting this charateristic, giving them ability to converse.

Heider and Simmel (1944)

Counterfeit People

  • Perils of this include counterfeit people.
  • Daniel Dennett has described the challenges these bring in an article in The Atlantic.

Psychological Representation of the Machine

  • But if correctly done, the machine can be appropriately “psychologically represented”

  • This might allow us to deal with the challenge of intellectual debt where we create machines we cannot explain.

In practice …

  • LLMs are already being used for robot planning Huang et al. (2023)

  • Ambiguities are reduced when the machine has had large scale access to human cultural understanding.

Inner Monologue

HAM

Networked Interactions

Thanks!

References

Andrade-Pacheco, R., Mubangizi, M., Quinn, J., Lawrence, N.D., 2014. Consistent mapping of government malaria records across a changing territory delimitation. Malaria Journal 13. https://doi.org/10.1186/1475-2875-13-S1-P5
Heider, F., Simmel, M., 1944. An experimental study of apparent behavior. The American Journal of Psychology 57, 243–259. https://doi.org/10.2307/1416950
Huang, W., Xia, F., Xiao, T., Chan, H., Liang, J., Florence, P., Zeng, A., Tompson, J., Mordatch, I., Chebotar, Y., Sermanet, P., Jackson, T., Brown, N., Luu, L., Levine, S., Hausman, K., ichter, brian, 2023. Inner monologue: Embodied reasoning through planning with language models, in: Liu, K., Kulic, D., Ichnowski, J. (Eds.), Proceedings of the 6th Conference on Robot Learning, Proceedings of Machine Learning Research. PMLR, pp. 1769–1782.
Lawrence, N.D., 2024. The atomic human: Understanding ourselves in the age of AI. Allen Lane.
Lawrence, N.D., 2010. Introduction to learning and inference in computational systems biology.
MacKay, D.M., 1991. Behind the eye. Basil Blackwell.
Mubangizi, M., Andrade-Pacheco, R., Smith, M.T., Quinn, J., Lawrence, N.D., 2014. Malaria surveillance with multiple data sources using Gaussian process models, in: 1st International Conference on the Use of Mobile ICT in Africa.
The Admiralty, 1945. The gunnery pocket book, b.r. 224/45.