Chris Eliasmith Tells You How to Build a Brain

 Artificial Intelligence  

In How to Build a Brain, artificial intelligence researcher Chris Eliasmith writes about the Semantic Pointer Architecture theory of intelligence, and how it was used to create the world's largest functional brain simulator, SPAUN.

One goal of researchers in neuroscience, psychology, and artificial intelligence is to build theoretical models that are able to explain the flexibility and adaptiveness of biological systems. In his book, How to Build a Brain: A Neural Architecture for Biological Cognition (Oxford Series on Cognitive Models and Architectures), Chris Eliasmith provides a detailed guided exploration of a new cognitive architecture that takes biological detail seriously, while addressing cognitive phenomena.

Eliasmith is the Canada Research Chair in Theoretical Neuroscience at the University of Waterloo

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.  SPA was used to creaate Eliasmith's SPAUN artificial intelligence system.

SPAUN is currently the world's largest functional brain simulation, and is unique because it's the first model that can actually emulate behaviors while also modeling the physiology that underlies them

Related articles IBM's Manoj Saxena on What Watson Will Mean for the Future  Stanford Researchers and Google Create World's Largest Artificial Neural Network  Chris Eliasmith Discusses SPAUN's Artificial Intelligence

Examples of other such models are provided in How to Build a Brain, and they are shown 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 these models introduces a major feature of biological cognition addressed in the book, including semantics, syntax, control, learning, and memory. These models are not introduced as independent considerations of brain function, but instead integrated to give rise to what is currently the world's largest functional brain model.

The last half of this book 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 this, 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. The book includes eight detailed, hands-on tutorials exploiting the free Nengo neural simulation environment, providing practical experience with the concepts and models presented throughout.

By 33rd Square

Embed