Lecture notes

• What the course is not about: symbolic systems
• Overview of neural networks
• Local and distributed representations
• An intelligent agent
• Search for an intelligent agent
• Evolutionary computation: the basics
• Evolutionary computation: variations
• Evolutionary computation: examples
• Introduction to reinforcement learning
• Q-learning examples
• Implementing reinforcement learning
• Delta rule and back-propagation
• Reinforcement learning variations
• Simple competitive learning
• Competitive learning variations
• Feature maps
• Dimensionality reduction
• Content-addressable memories: Hopfield networks
• Perceptrons
• Back-propagation variations
• Sparse distributed memory and RBF networks
• Generative models
• Handling time
• Hopfield networks with delays
• Learning inverse kinematics
• The binding problem
• Evolution and learning
• Modularity
• Constructivist networks

© 2009. Indiana University and Michael Gasser. www.cs.indiana.edu/classes/b553/notes.html 2009-04-23