Here’s your roadmap for the semester!

  • Readings should be completed before each class session
  • Assignments are due by 11:59 PM on the day they are due
  • Class materials (slides, in-class activities, etc.) will be added on the day of class

Simple Neural Networks Reading Assignment Class
September 1 Learning in Humans and Machines
September 3 R, RStudio, and Github
September 8 Associative Learning
September 10 How far can simple associative learning get you?
September 15 Perceptrons
September 16 Implementing the Rescorla-Wagner Model
September 17 Multi-layer Networks
September 22 Backpropagation details
September 24 Limits to connectionism
September 29 Recurrent neural networks
October 9 Perceptrons and backpropagation
Bayesian learning Reading Assignment Class
October 1 Basics of Bayesian Inference
October 6 Learning by Bayesian inference
October 8 Models at different levels
October 13 Rational analysis
October 15 Inference by sampling
October 20 Bayesian associative learning
October 21 The number game
October 22 Comparing models
October 27 Machines that learn like people
November 6 Markov chain Monte Carlo
Learning from other people Reading Assignment Class
October 29 Learning from teaching
Nov 3 What makes a good teacher?
Nov 5 Rational speech acts
Nov 6 Project Proposal
Nov 10 Indirectly learning from language
Nov 12 Iterated learning
Nov 17 Community effects on learning from others
Nov 19 The structure in language
Nov 24 Modern language models
Nov 26 Thanksgiving - No class
Dec 1 Why training data matter
Projects Reading Assignment Class
Dec 3 Project Presentations
Dec 8 Project Presentations
Dec 10 Wrap up
December 15 Final Project due