How to Build a Brain: A Neural Architecture for Biological Cognition

by Chris Eliasmith

How to Build a Brain provides a detailed exploration of a new cognitive architecture - the Semantic Pointer Architecture - that takes biological detail seriously, while addressing cognitive phenomena. Topics ranging from semantics and syntax, to neural coding and spike-timing-dependent plasticity are integrated to develop the world's largest functional brain model.

Genres: Neuroscience, Artificial Intelligence, Science, Nonfiction, Brain, Computer Science, Psychology

480 pages, Kindle Edition

First published January 1, 2013

Reviews

[Cal Godot · Rating 4 out of 5]

This book kicks ass, but I'm not intelligent enough to convey anything more.

[Martin · Rating 5 out of 5]

interesting book. highly technical, so it's not really for the lay reader.

[Marius · Rating 2 out of 5]

Looks like the main purpose of this book is to make the author look knowledgeable, and to promote their Nengo project. Clearly the author knows a lot, but he doesn't have the skills to pass that to non-experts.

[Parsa]

Don’t be fooled by the intro, you need a pretty good foundation in control theory and linear algebra to get anything out of this. Still, the SPA is a pretty cool use of vector spaces even though I still haven’t quite wrapped my head around it.