Blog
About

121
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      The Helmholtz machine.

      Neural computation

      Stochastic Processes, Algorithms, Feedback, Humans, Models, Psychological, Pattern Recognition, Automated, Pattern Recognition, Visual, Perception, physiology

      Read this article at

      ScienceOpenPubMed
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Most cited references 10

          • Record: found
          • Abstract: not found
          • Article: not found

          A learning algorithm for boltzmann machines

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            The "wake-sleep" algorithm for unsupervised neural networks

             R. Neal,  B. Frey,  P. Dayan (1995)
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Connectionist learning of belief networks

               Radford Neal (1992)
                Bookmark

                Author and article information

                Journal
                7584891

                Comments

                Comment on this article