Theoretical Foundations of Cognitive Agents | Prof. Johan Kwisthout
@index
Lecturer: Johan Kwisthout .
- Philosophy block: 1-3
- Foundations: 4-6
- The MAP problem: 7-8
- Computational models: 9-11
1: Explainable AI
- Pearl-Theoretical_impediments_machine_learning.md
- Kind-Intentional stance
- McCarthy-Ascribing mental qualities to machines
- Gunning: DARPA report on XAI (sufficient notes in lecture 1)
2: Abduction
- Burks-Peirces theory of abduction
- Harman-The_inference_to_the_best_explanation.md
- Lipton-Inference_to_the_best_explanation.md
- Glass-Does_inference_to_the_best_explanation_track_truth.md
- N.B. only the first section is mandatory for this course (I only found out later though)
3: Frame problem
- Dennett-Cognitive wheels, the frame problem in AI
- Haselager-Cognitive_Science_Folk_Psychology_The_Right_Frame_of_Mind.md
4: Bayesianism
We focus on the epistemological interpretation of Bayesianism, i.e. on probabilities as subjective degrees of belief.
The Easwaran papers concern the question: What are the arguments for (and against) Bayesianism as a philosophical stance?
Fiorillo and Jeffrey excerpts concern the question where priors should come from, and how beliefs should be updated.
Lecture 4: Uncertainty and Bayesianism
- Easwaran, arguments in favor of Bayesianism
- Easwaran-Bayesianism_II.md
- Fiorillo, Beyond Bayes
- Jeffrey-Probability Kinematics
- TODO unfinished, left at page 170, relevance section.
5: Bayes in Cognitive Science and Neuro Science
-
Bowers and Davis - Bayesian just-so stories in psychology and neuroscience.md
- Includes a response
Main concepts:
- Bayesian Brain Hypothesis
- Free Energy Principle
- Predictive Coding
- Predictive Processing
6: Stochastic Computations
7: The MAP problem
Can be interpreted as the Bayesian network implementation of IBE.
8: Approximations of MAP
9: Relevancy
- TFCA-9-Relevancy.md
- Relevancy paper is included in here
10: Probable + Informative: Most inforbable explanations
TFCA-10-Inforbable_explanations.md * Paper notes included in here as well
11: Marc Blokpoel guest lecture on Analogical Inference
Some relevant concepts
- Frequentist versus Subjective Probability
- Subjective vs. objective Bayesianism
- Maximum Entropy Principle
- Dutch-book arguments
- Quine-Duhem thesis
- Tacit Communication Game (TCG)
- Nicods_criterion
Project
Project done reading:
- Lipton-Inference_to_the_best_explanation.md
- Glass-Does_inference_to_the_best_explanation_track_truth.md
- Henderson (2014) -Bayesianism_and_Inference_to_the_Best_Explanation.md
- Weisberg-Locating_IBE_in_Bayesian_framework.md
- Harman-The_inference_to_the_best_explanation.md
- Henderson (2017)-Bayesianism_and_IBE.md
- Bird-IBE, Bayesianism, Knowledge
Next:
- Poston - Bayesian Explanationism
Investigate constraint-based compatibilism:
- NOT IN READING LIST YET Okasha, S. [2000]: ‘Van Fraassen’s Critique of Inference to the Best Explanation’, Studies in History and Philosophy of Science, 31, pp. 691–710.
- Lipton 2004 (the book)
- Huemer, M. [2009a]: ‘Explanationist Aid for the Theory of Inductive Logic’, British
Journal for the Philosophy of Science, 60, pp. 345–75.
- See Henderson 2014. Explanationist aid to objective Bayesianist; similar to Weisberg 2009.
- Weisberg 2009: Locating IBE in the Bayesian framework
Marginally relevant: