Given the practical nature of much of the material in the book, it can be used quite successfully as a textbook for a course on cognitive or neural modelling. The material below will assist instructors in running such a course.

Note: If you are looking for something specific (e.g. specific slides, images, code, etc.), please do not hesitate to contact Chris Eliasmith

Suggested lecture schedule

I've provided more lectures than I believe you can fit in a single term. However, this allows lecturers to add and remove topics as they see fit, or change the emphasis of a particular version of the course. I'm assuming that each lecture is 3 hours (i.e. a typical week's worth of material).

Lecture Readings Topics Assignment
Week 1 Sections 1.1 & 1.2: The Science of Cognition
  • A brief history of cognitive science
  • Central features of the main approaches
Install and run Nengo
Week 2 Sections 1.3 & 1.4
  • Challenges for cognitive science
  • Overview of the approach in this course
Build a model of a single neuron
Week 3 Sections 2.2 & 2.2.1
  • An introduction to basic neurophysiology and anatomy
  • Principle 1 of the NEF: representation
Build a model of 1D representation
Week 4 Section 2.2.2
  • Principle 2 of the NEF: computation
Build a model that computes linear and nonlinear functions of a single variable
Week 5 Section 2.2.3
  • Principle 3 of the NEF: dynamics
Build a model of a 1D integrator
Week 6 (optional) Section 2.6
  • Levels of description in the behavioral sciences
Build a model at 3 levels of description
Week 7 Sections 3.1–3.4
  • Overview of the semantic pointer hypothesis
  • Distributed neural semantics
Build a model of 2D (or higher-D) representation
Week 8 Sections 3.5–3.7
  • An introduction to visual semantics
  • An introduction to motor semantics
Build a model of 2D nonlinear computation (multiplication)
Week 9 Sections 4.1–4.4 & 4.6
  • Syntactic representations
  • Vector symbolic architectures
  • Implementations of VSAs in neurons
Build a binding neural network
Week 10 (optional) Sections 4.5–4.7
  • Learning syntactic manipulations
  • Modeling fluid intelligence
  • Syntax and semantics for structured concepts
Build a model that learns an unknown syntactic transformation
Week 11 Sections 5.1–5.3
  • Basal ganglia anatomy and physiology
  • Basal ganglia function
Build a basal ganglia model that selects among 5 actions
Week 12 Sections 5.4, 5.6–5.8
  • Basal ganglia use for flexible action selection
  • Example uses of the basal ganglia model in the SPA
Build a question answering model with control
Week 13 Sections 6.1–6.3
  • Introduction to cognition through time
  • Working memory and serial working memory
Build a (serial) working memory model
Week 14 Sections 6.4–6.6
  • Spike-timing dependent plasticity (STDP)
  • Reinforcement learning
  • Learning transformations with the hPES rule
Build a network that learns an arbitrary 1D transformation
Week 15 Sections 7.1–7.3
  • A review and overview of the SPA
  • The Spaun model and tasks
Build a question answering model with control
Week 16 (optional) Section 7.4
  • Probabilistic models
  • Interpreting the SPA as a probabilistic model
Build a model to do a simple statistical inference problem
Week 17 Chapter 8
  • Evaluating cognitive theories
  • Detailed discussion of the core cognitive criteria
Begin a course project, using tutorial 8 as an example
Week 18 Chapter 9
  • A survey of other approaches to cognitive modelling
  • A comparison of the SPA with past approaches
Course project
Week 19 Chapter 10
  • Conceptual consequences of the SPA and NEF methods
  • Future challenges for this and other approaches
Course project

Assignment details

The assignments above mirror those in the book. It is also useful to ask questions about the functioning of the models being built, and to ask students to change the models slightly to examine different aspects of neural/cognitive processing. The intent of this section of the website is to provide examples of such questions, as we develop them. Suggestions welcome.

Suggested projects

  • Build a creature to seek food and return to a home nest.

  • Build a serial working memory model that allows for loading, reset, etc.

  • Build a robot controller for a robot that you present instructions to, that it memorizes and then executes.

  • Build an adaptive controller for a 3-link arm using Slotine's adaptation methods.

  • Build a model that does any one of the tasks in Spaun.

  • Build something on the modelling ideas list.

If you have a project suggestions, please add it to the modelling ideas list, or post it on the Nengo forum.