Wishlist
Book Summary
Introduction to Connectionist Modelling of Cognitive Processes is a textbook by Peter McLeod, Kim Plunkett, and Edmund Rolls that explains how neural network models simulate cognition. It covers fundamental connectionist principles, learning algorithms, and applications to memory, language, and categorization. Ideal for students and researchers seeking a rigorous, accessible foundation in computational cognitive science.
This book is not available
Store  |
Condition |
Deals & Coupons | Price |
Est. Shipping |
Total |
Buy |
|---|---|---|---|---|---|---|
| Sorry we could not find any result for “9780198524267” | ||||||
About Introduction To Connectionist Model...
This textbook provides a comprehensive introduction to connectionist modelling, the approach that uses artificial neural networks to understand cognitive processes. Written by leading researchers Peter McLeod, Kim Plunkett, and Edmund Rolls, it guides readers from basic concepts—such as units, weights, and activation functions—through to advanced topics like recurrent networks and self-organizing maps. The book emphasizes how these models can be applied to real cognitive phenomena, including memory, language acquisition, categorization, and decision-making. Each chapter includes clear explanations, illustrative examples, and practical exercises, making complex mathematical ideas accessible. It balances theoretical foundations with hands-on modelling, helping readers develop the skills to build and evaluate their own connectionist models. This makes it an essential resource for advanced undergraduates, graduate students, and researchers in psychology, cognitive science, and neuroscience who want to understand how neural networks can illuminate the workings of the mind.
Who should read Introduction To Connectionist Model...?
This book is ideal for advanced undergraduates, graduate students, and researchers in cognitive science, psychology, neuroscience, and artificial intelligence who want a rigorous yet accessible introduction to connectionist modelling. It suits readers with some background in basic mathematics and programming, though prior expertise in neural networks is not required. Instructors teaching courses on computational cognitive science will find it a valuable core text, and researchers seeking to incorporate connectionist methods into their work will benefit from its practical guidance and theoretical depth.
Pros & Cons
Pros
- ✓ Clear, pedagogical explanations make complex connectionist concepts accessible to newcomers.
- ✓ Authored by leading experts, ensuring authoritative and up-to-date content.
- ✓ Balances theory with practical modelling exercises and examples.
- ✓ Covers a broad range of cognitive applications, from memory to language.
- ✓ Includes exercises and further reading to support self-study and coursework.
Cons
- ✗ Some mathematical sections may be challenging for readers without a quantitative background.
- ✗ Focuses primarily on classical connectionist models; may not cover the latest deep learning advances.
- ✗ Assumes some familiarity with programming, which could limit accessibility for pure beginners.
- ✗ Limited coverage of certain cognitive domains, such as emotion or social cognition.
- ✗ The book's age means some examples and references may feel dated to contemporary readers.
Similar books
Frequently asked questions
Do I need prior programming experience to understand this book?
Some familiarity with programming is helpful, as the book includes practical modelling exercises, but the core concepts are explained clearly enough that motivated readers can follow along with basic coding knowledge.
Is this book suitable for self-study?
Yes, the book is designed with pedagogical features such as exercises, examples, and further reading, making it well-suited for independent study by advanced students and researchers.
Does it cover recent deep learning techniques?
The book focuses on foundational connectionist models rather than the latest deep learning architectures, so readers seeking cutting-edge coverage may need to supplement with more recent texts.
What background in mathematics is required?
A basic understanding of algebra and some familiarity with calculus and linear algebra will help, but the authors explain key mathematical concepts as they arise, so extensive prior training is not essential.
Is this book appropriate for undergraduate courses?
It is well-suited for advanced undergraduate and graduate courses in cognitive science, psychology, and neuroscience, particularly those focused on computational modelling.
At Windsorbooks, we compare prices from trusted sellers so you can buy, rent, or sell textbooks at the best total price — shipping included.
As an Amazon Associate, Windsorbooks.com may earn a small commission on qualifying purchases.