Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks

A practical book, Neural Smithing is aimed at the reader who intends to design and build neural networks for applications from forecasting to pattern recognition. The authors concentrate on multilayer perceptrons (MLPs) as the most commonly used neural network model, which adds to the book's overall clarity and focus.

This textbook-style reference begins with simple, single-layer networks and the elements of supervised learning. It then builds on these basics with such topics as error surfaces, genetic algorithms, and generalization. Examples and illustrations guide the reader through the discussion, but the authors don't suggest problems for further study--a small omission in an otherwise well-constructed book.

Readers must know calculus and statistics to make sense of the text, but they don't need much knowledge of neural computing. Whether used as an introductory textbook or as a professional reference, Neural Smithing is highly useful. Tightly focused and easy to use, it should have a place next to every neural toolbox. --Rob Lightner

• Deep Learning (Adaptive Computation and Machine Learning series)
• Neural Networks for Pattern Recognition (Advanced Texts in Econometrics (Paperback))
• Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play
• Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning series)
• Deep Learning with Python
• Neural Network Design (2nd Edition)
• Computer Vision: Models, Learning, and Inference
• Deep Learning and the Game of Go
• Introduction to Applied Linear Algebra: Vectors, Matrices, and Least Squares
• Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning) (Adaptive Computation and Machine Learning series)