Item description for Understanding Brain and Mind: A Connectionist Perspective by Yehuda Salu...
How can we understand a system as complex as the brain? Does the brain use the same operational principles to control physical and mental activities? How can we incorporate in a model what we know and what we do not know about the brain? The connectionist model presented in this book provides tools for addressing such questions. Its nodes represent well-established biological facts combined with observations of the overall behaviours of the system. The model is based on comparing and contrasting brains, computers, and neural networks. It defines a framework for understanding the relationships between the brain and the mind. It can serve both as a starting point for developing artificial intelligence applications for all levels of mental activities and as a guide in the search for biological correlates of observed behaviours.
Promise Angels is dedicated to bringing you great books at great prices. Whether you read for entertainment, to learn, or for literacy - you will find what you want at promiseangels.com!
Studio: World Scientific Publishing Company
Est. Packaging Dimensions: Length: 8.78" Width: 6.34" Height: 0.76" Weight: 1.11 lbs.
Publisher World Scientific Publishing Company
ISBN 9810247923 ISBN13 9789810247928
Availability 0 units.
More About Yehuda Salu
The author is a physics professor at Howard University. He studied the electrical activity of the brain and the heart in collaboration with scientists at the NIH and the University of Iowa. He developed neural networks for analyzing satellite images in collaboration with NASA scientists. His other books are "Understanding Brain and Mind; a connectionist perspective" and "Physics for Architects."
Reviews - What do customers think about Understanding Brain and Mind: A Connectionist Perspective?
Great representation structures, but no simulations Oct 7, 2009
This is a very interesting book. Its strong points include a wealth of information structures by which neural networks may represent knowledge and meta-knowledge, including structures that might be used to "think" about hypotheses. Its largest weakness is that there are absolutely no data runs or simulations done, which seems very odd. It thus provides a blueprint for the construction of an artificial neural network that may have significant information processing and modeling capabilities, although there is no way to evaluate this without writing all the code oneself. Despite this shortcoming, I recommend the book for those interested in high level knowledge instantiation in neural nets because of the wealth of interesting representation structures discussed.