How to Build a Brain: A Neural Architecture for Biological Cognition (Oxford Series on Cognitive Models and Architectures)

In this book, Chris Eliasmith presents a new approach to understanding the neural implementation of cognition in a way that is centrally driven by biological considerations. He calls the general architecture that results from the application of this approach the Semantic Pointer Architecture (SPA), based on the Semantic Pointer Hypothesis. According to this hypothesis, higher-level cognitive functions in biological systems are made possible by semantic pointers. These pointers are neural representations that carry partial semantic content and can be built up into the complex representational structures necessary to support cognition. The SPA architecture demonstrates how neural systems generate, compose, and control the flow of semantics pointers. Eliasmith describes in detail the theory and empirical evidence supporting the SPA, and presents several examples of its application to cognitive modeling, covering the generation of semantic pointers from visual data, the application of semantic pointers for motor control, and most important, the use of semantic pointers for representation of language-like structures, cognitive control, syntactic generalization, learning of new cognitive strategies, and language-based reasoning. He agues that the SPA provides an alternative to the dominant paradigms in cognitive science, including symbolicism, connectionism, and dynamicism.