Neurons and Symbols: The Stuff the Mind is Made of

by Igor Aleksander, Helen Morton

"Neurons and Symbols", the successor to the authors' work "An Introduction to Neural Computing", presents in a unified explanatory style the emerging points of a fierce contemporary debate on the effect that neural models are likely to have on more classic symbolic models of cognition. The controversy is multi-disciplinary - it involves scientists and technologists who are trying to build machines with cognitive properties, computer theoreticians interested in artificial intelligence, cognitive scientists and psychologists who are trying to find appropriate representations for cognition, philosophers who would like to explain concepts of the mind and linguists who are concerned with the role of language in cognition. The non-mathematical approach of this book lays bare the arguments that are put forward by those who, on the one hand, believe that the way to understand cognition is by knowing what the neural networks of the brain are doing, and on the other, those who believe that a program-like symbolic representation is the way to explain things. Is there a compromise between the two? The authors believe that there is and present the results of their own research in the area. Being interdisciplinary, one of the aims of the book is to start from first principles in everything, providing the reader with sufficient background in neural systems, artificial intelligence, cognitive science, automata theory and computational theory.

256 pages, Paperback

First published January 1, 1993

Reviews

[George Marshall · Rating 4 out of 5]

I enjoyed grappling with this book. The author is capable, and applies analogy and fact to great effect. While I struggled at first to envision the concept of states emerging from the neural network, the author convincingly demonstrates how our experience can be implemented and supported in this state system. As he does it he seems aware of himself to an astounding degree: where more research is required, where tests can demonstrate coherence between theory and reality, where the next steps are.

And probably more impressive, and personally pleasing, is his extensive and specific references to relevant source material. I was able to procure a larger than necessary set of reading materials from my local university library to further my understanding, from a bibliography offering mechanical implementation of sensory input, psychology, neuroscience, cognition, computation, and artificial intelligence. Oh, and plenty of philosophy of mind.

Bottom line, early and great synthesis with lots of jumping off points for further study.