Bayesian learning for neural networks
Bayesian learning for neural networks
复制标题
DOI：
10.1007/978-1-4612-0745-0
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
Radford M. Neal
中科院分区：
文献类型：
--
作者：
Radford M. Neal
人工“神经网络”被广泛用作分类和回归应用的灵活模型，但在训练数据有限的情况下，如何安全地利用这些模型的功能仍然存在问题。本书演示了贝叶斯方法如何允许使用复杂的神经网络模型，而不必担心传统训练方法可能出现的“过拟合”。深入了解这些复杂贝叶斯模型的本质是通过对它们背后的先验函数的理论研究提供的。本文还描述了使用马尔可夫链蒙特卡罗方法的贝叶斯神经网络学习的实际实现，并且它的软件可以在互联网上免费获得。假设只有概率和统计的基本知识，这本书应该感兴趣的研究人员在统计，工程和人工智能。
Artificial" neural networks" are widely used as flexible models for classification and regression applications, but questions remain about how the power of these models can be safely exploited when training data is limited. This book demonstrates how Bayesian methods allow complex neural network models to be used without fear of the" overfitting" that can occur with traditional training methods. Insight into the nature of these complex Bayesian models is provided by a theoretical investigation of the priors over functions that underlie them. A practical implementation of Bayesian neural network learning using Markov chain Monte Carlo methods is also described, and software for it is freely available over the Internet. Presupposing only basic knowledge of probability and statistics, this book should be of interest to researchers in statistics, engineering, and artificial intelligence.