Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

The measurement of meaning

Explanation in artificial intelligence: Insights from the social sciences

Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

/pdf/building-machines-that-learn-and-think-like-people-w8p3qwruiy.pdf

Building machines that learn and think like people.

Foundations Of Statistics

https://www.ucl.ac.uk/lagnado-lab/publications/lagnado/judgments%20of%20cause%20and%20blame.pdf

Judgments of cause and blame: The effects of intentionality and foreseeability

Can people learn causal structure more effectively through intervention rather than observation? Four studies used a trial-based learning paradigm in which participants obtained probabilistic data about a causal chain through either observation or intervention and then selected the causal model most likely to have generated the data. Experiment 1 demonstrated that interveners made more correct model choices than did observers, and Experiments 2 and 3 ruled out explanations for this advantage in terms of informational differences between the 2 conditions. Experiment 4 tested the hypothesis that the advantage was driven by a temporal signal; interveners may exploit the cue that their interventions are the most likely causes of any subsequent changes. Results supported this temporal cue hypothesis.

https://www.ucl.ac.uk/lagnado-lab/publications/lagnado/advantage%20of%20timely%20intervention.pdf

The Advantage of Timely Intervention.

https://www.ucl.ac.uk/lagnado-lab/publications/lagnado/DoWeDo.pdf

Do We "do"?

© 2007 by Alison Gopnik and Laura Schulz All rights reserved Causal induction has two components: learning about the structure of causal models and learning about causal strength and other quantitative parameters This chapter argues for several interconnected theses First, people represent causal knowledge qualitatively, in terms of causal structure; quantitative knowledge is derivative Second, people use a variety of cues to infer causal structure aside from statistical data (eg temporal order, intervention, coherence with prior knowledge) Third, once a structural model is hypothesized, subsequent statistical data are used to confirm, refute, or elaborate the model Fourth, people are limited in the number and complexity of causal models that they can hold in mind to test, but they can separately learn and then integrate simple models, and revise models by adding and removing single links Finally, current computational models of learning need further development before they can be applied to human learning

/pdf/beyond-covariation-cues-to-causal-structure-3pmk3lytu1.pdf

Beyond covariation: Cues to causal structure.

https://www.ucl.ac.uk/lagnado-lab/publications/lagnado/moore%20et%20al%20causal%20control.pdf

David A. Lagnado

Papers

Judgments of cause and blame: The effects of intentionality and foreseeability

The Advantage of Timely Intervention.

Do We "do"?

Beyond covariation: Cues to causal structure.

Feelings of control: contingency determines experience of action.