Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks
Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks
复制标题
DOI：
10.1088/0954-898x_6_3_011
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
D. MacKay
中科院分区：
文献类型：
--
作者：
D. MacKay
贝叶斯概率论为数据建模提供了统一的框架。在这个框架中，总体目标是找到与数据匹配良好的模型，并使用这些模型做出最佳预测。神经网络学习被解释为对给定训练数据的模型的最可能参数的推断。然后，在模型空间（即架构、噪声模型、预处理、正则化器和权重衰减常数的空间）中的搜索也可以被视为一个推理问题，在这个问题中，我们推断出给定数据的替代模型的相对概率。这篇综述描述了基于高斯近似的实用技术，用于实现这些强大的方法来控制、比较和使用自适应网络。
Bayesian probability theory provides a unifying framework for data modelling. In this framework the overall aims are to find models that are well-matched to the data, and to use these models to make optimal predictions. Neural network learning is interpreted as an inference of the most probable parameters for the model, given the training data. The search in model space (i.e., the space of architectures, noise models, preprocessings, regularizers and weight decay constants) can then also be treated as an inference problem, in which we infer the relative probability of alternative models, given the data. This review describes practical techniques based on Gaussian approximations for implementation of these powerful methods for controlling, comparing and using adaptive networks.