Artificial \"neural networks\" have become essential tools in classification and regression applications due to their flexibility. However, the challenge remains in safely harnessing their power, especially when training data is limited. This book offers a compelling solution by demonstrating how Bayesian methods can be employed to utilize complex neural network models effectively, mitigating the risk of \"overfitting\" that often accompanies traditional training techniques.
The book delves into the theoretical aspects of Bayesian models, providing insight into the priors over functions that form their foundation. This theoretical investigation is crucial for understanding the nature of these complex models. Furthermore, the book describes a practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods, with software available for free on the Internet.
Designed for readers with a basic understanding of probability and statistics, this book is a valuable resource for researchers in statistics, engineering, and artificial intelligence. It bridges the gap between theory and practice, offering both a deep theoretical exploration and practical tools for Springer
Author: Neal, Radford M.Genre: Probability & StatisticsBinding: PaperbackFormat: IllustratedPublication Date: 1996Edition: 1996Series Title: Lecture Notes in Statistics, 118
When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.