DeepLearning
CS5001
Lectures for the weeks of:
2018-10-15
Probability, Markov
chains
- Reading:
- Chapter 8, ArtInt:
https://artint.info/2e/html/ArtInt2e.Ch8.html
- Slides:
2018-10-22
Rationality, utility,
decisions
- Reading:
- Chapter 9, ArtInt:
https://artint.info/2e/html/ArtInt2e.Ch9.html
- Sildes:
- Code: https://artint.info/AIPython/aipython.pdf (explained here)
- https://artint.info/AIPython/aipython/mdpProblem.py
- https://artint.info/AIPython/aipython/mdpExamples.py
- Visualizations:
2018-10-29
Reinforcement learning
(RL)
- Slides:
- Reading:
- Chapter 12 (skip 10, 11):
https://artint.info/2e/html/ArtInt2e.Ch12.html
- DeepLearning/RL_survey_Kaelbling1996.pdf
- http://www.scholarpedia.org/article/Reinforcement_learning
- http://www.scholarpedia.org/article/Temporal_difference_learning
- https://en.wikipedia.org/wiki/Reinforcement_learning
- https://en.wikipedia.org/wiki/Q-learning
- https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action
- Visualizations:
- Code: https://artint.info/AIPython/aipython.pdf (explained here)
- https://artint.info/AIPython/aipython/rlProblem.py
- https://artint.info/AIPython/aipython/rlSimpleEnv.py
- https://artint.info/AIPython/aipython/rlQLearner.py
- https://artint.info/AIPython/aipython/rlModelLearner.py
- https://artint.info/AIPython/aipython/rlFeatures.py
- https://artint.info/AIPython/aipython/rlSimpleGameFeatures.py
- https://artint.info/AIPython/aipython/rlPlot.py
- Assignment:
Neural nets (NN)
- Code: https://artint.info/AIPython/aipython.pdf (explained here)
- https://artint.info/AIPython/aipython/learnNN.py (not simple
enough…)
- More coming soon!
- Slides:
- Reading: