THE HELMHOLTZ MACHINE
THE HELMHOLTZ MACHINE
复制标题
DOI：
10.1162/neco.1995.7.5.889
复制
发表时间：
1995-09-01
影响因子：
2.9
通讯作者：
ZEMEL, RS
中科院分区：
文献类型：
--
作者：
DAYAN, P;HINTON, GE;ZEMEL, RS
发现一组模式中固有的结构是统计推断或学习的基本目标。一个富有成效的方法是建立一个参数化的随机生成模型，独立的提请可能产生的模式。除了最简单的生成模型，每个模式都可以以指数级的方式生成。因此，难以调整参数以最大化观察到的模式的概率。我们描述了一种巧妙的方法，通过最大限度地提高一个容易计算的下限的概率的意见，这种组合爆炸。我们的方法可以被视为一种分层自监督学习的形式，可能与自下而上和自上而下的皮质处理路径的功能有关。
Discovering the structure inherent in a set of patterns is a fundamental aim of statistical inference or learning. One fruitful approach is to build a parameterized stochastic generative model, independent draws from which are likely to produce the patterns. For all but the simplest generative models, each pattern can be generated in exponentially many ways. It is thus intractable to adjust the parameters to maximize the probability of the observed patterns. We describe a way of finessing this combinatorial explosion by maximizing an easily computed lower bound on the probability of the observations. Our method can be viewed as a form of hierarchical self-supervised learning that may relate to the function of bottom-up and top-down cortical processing pathways.