Chris Eliasmith - Böcker

One goal of researchers in neuroscience, psychology, and artificial intelligence is to build theoretical models that can explain the flexibility and adaptiveness of biological systems. How to Build a Brain provides a guided exploration of a new cognitive architecture that takes biological detail seriously while addressing cognitive phenomena. The Semantic Pointer Architecture (SPA) introduced in this book provides a set of tools for constructing a wide range of biologically constrained perceptual, cognitive, and motor models. Examples of such models are provided to explain a wide range of data including single-cell recordings, neural population activity, reaction times, error rates, choice behavior, and fMRI signals. Each of the models addressed in the book introduces a major feature of biological cognition, including semantics, syntax, control, learning, and memory. These models are presented as integrated considerations of brain function, giving rise to what is currently the world's largest functional brain model. The book also compares the Semantic Pointer Architecture with the current state of the art, addressing issues of theory construction in the behavioral sciences, semantic compositionality, and scalability, among other considerations. The book concludes with a discussion of conceptual challenges raised by this architecture, and identifies several outstanding challenges for SPA and other cognitive architectures. Along the way, the book considers neural coding, concept representation, neural dynamics, working memory, neuroanatomy, reinforcement learning, and spike-timing dependent plasticity. Eight detailed, hands-on tutorials exploiting the free Nengo neural simulation environment are also included, providing practical experience with the concepts and models presented throughout.

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.