Customer Reviews

Artificial Intelligence and Neural Networks: Steps Toward Principled Integration (Neural Networks: Foundations to Applications)

5 star:		(2)
4 star:		(0)
3 star:		(0)
2 star:		(0)
1 star:		(0)

 

 

This book is an excellent reference book on current approaches to some of the foundational questions in artificial intelligence, philosophy of mind, and engineering of intelligent systems. The editors as amply demonstrated by their other publications, have the rare ability to interrelate an amazing diversity of perspectives on Artificial Intelligence - from symbolic methods to neural networks and evolutionary apporaches, to uncover the shared principles and common foundations, and show how different paradigms can be brought together in synergistic ways to advance our ability to design and analyze intelligent systems. This book includes chapters written by some of the leading experts in the field. The book should be especially useful as a reference to graduate students and researchers interested in artificial intelligence, machine learning, cognitive science, software agents, and philosophy of mind. It should also be useful as supplementary reading for a graduate or upper level undergraduate course in artificial intelligence or cognitive science, or as a primary text for a seminar course. All in all, a great book!

Symbolic (e.g., logic based) and connectionist (e.g., neural network) models are often viewed as separate, and perhaps incompatible approaches to artificial intelligence and cognitive modelling. Far too many young researchers (including myself) have been swept away by the exaggerated claims of each camp. This collection of chapters is an excellent medicine for such a malaise. The chapters in this collection demonstrate, with pursuasive theoretical and philosophical arguments as well as empirical data that symbolism and connectionism can, and perhaps should, be reconciled. At the time this book came out, this was not a popular position. However, recent developments in AI and cognitive science have more than vindicated the views expressed in this book. Now (6 years later), some of the chapters are a bit dated. However, I recommend the book strongly to those who are interested in foundational issues in artificial intelligence and cognitive science.