Nadas A
Res. Div., IBM Thomas J. Watson Res. Center, Yorktown Heights, NY.
IEEE Trans Neural Netw. 1995;6(2):488-91. doi: 10.1109/72.363484.
We classify points in R(d) (feature vector space) by functions related to feedforward artificial neural networks. These functions, dubbed "stochastic neural nets", arise in a natural way from probabilistic as well as from statistical considerations. The probabilistic idea is to define a classifying bit locally by using the sign of a hidden state-dependent noisy linear function of the feature vector as a new (d+1)th coordinate of the vector. This (d+1)-dimensional distribution is approximated by a mixture distribution. The statistical idea is that the approximating mixtures, and hence the a posteriori class probability functions (stochastic neural nets) defined by them, can be conveniently trained either by maximum likelihood or by a Bayes criterion through the use of an appropriate expectation-maximization algorithm.
我们通过与前馈人工神经网络相关的函数对R(d)（特征向量空间）中的点进行分类。这些函数被称为“随机神经网络”，它们以自然的方式源于概率以及统计方面的考虑。概率方面的想法是通过使用特征向量的依赖于隐藏状态的噪声线性函数的符号作为向量的新的（d + 1）维坐标来局部定义一个分类位。这个（d + 1）维分布由混合分布近似。统计方面的想法是，近似混合以及由此由它们定义的后验类概率函数（随机神经网络）可以通过使用适当的期望最大化算法，方便地通过最大似然法或贝叶斯准则进行训练。
