Connectionist Models of Cognition BrainWave Logo

Created by Simon Dennis and Devin McAuley

Connectionist Models of Cognition is a web-based textbook designed to introduce the key concepts in the area of neural networks. It targets both faculty and students interested in the application of parallel distributed processing models to cognitive phenomena either in a teaching or research capacity. The textbook provides hands-on modeling experience with a variety of standard architectures and the opportunity to begin developing your own models. A background in connectionist theory is not required.

The BrainWave connectionist simulator is embedded within the materials, allowing you to interact with the figures as you work through the exercises. The simulator employs a graphical, direct manipulation interface - much like a drawing program - making it easy to use.

The BrainWave simulator showing the Jets and Sharks Network (McClelland, 1981).
Click on the Art unit and then the Cycle button to see the network in operation.

The architectures that are currently implemented include the Interactive Acitivation and Competition network, the Hebbian Network, the Backpropagation network, the Hopfield network, the Self Organizing Map and the Simple Recurrent Network. The software is easily extensible to new architectures.

Access to the textbook is FREE for individuals. So that we can keep track of who is using the text we require you to register. Once you have registered a password will be sent to you that will provide access to the chapters. If you are an instructor intending to use the text in a course we ask that you purchase a site license. To access the materials we recommend using Internet Explorer 4.0/5.0 or Netscape 4.x on Windows 95/98/NT.

Table of Contents

  1. Preface: How to use the materials by Simon Dennis and Devin McAuley
  2. Introduction to Neural Networks by Simon Dennis
  3. Introduction to the BrainWave Simulator by Devin McAuley and Simon Dennis
  4. The Interactive Activation and Competition Network: How Neural Networks Process Information by Simon Dennis
  5. The Hebbian Network: The Distributed Representation of Facts by Janet Wiles, Simon Dennis and Rachael Gibson
  6. The Hopfield Network: Descent on an Energy Surface by Simon Dennis
  7. The Backpropagation Network: Learning by Example by Devin McAuley and Simon Dennis
  8. The Self-Organizing Map: Unsupervised Competitive Learning by Simon Dennis and Janet Wiles
  9. Context Effects in Letter Perception by Devin McAuley and Simon Dennis
  10. Controlled and Automatic Processing by Devin McAuley, Janet Wiles and Simon Dennis
  11. Long Term Memory: Matching versus Retrieval, Episodic versus Semantic by Simon Dennis and Rachael Gibson
  12. Answers to Exercises Contact us at if you are an instructor wanting to obtain a password to the answers page