Information geometry on ensemble hme model*

  • Hua W
  • 2


    Mendeley users who have this article in their library.
  • 0


    Citations of this article.


An extendable framework is developed for ensemble HME model based on the theory analysis of information geometry. In a hierarchical set of systems, a lower order system is included in the parameter space of a large one as a subset. Such a parameter space has rich geometrical structures that are responsible for the dynamic behaviors of learning. HME network divides a task into small tasks by the principle of divide and conquer to improve the performance of a single network. By studying the dual manifold architecture for mixtures of neural networks and analyzing the probability of Knowledge-increasable Model based on information geometry, the paper proposes a new method to achieve the multi-HME model that has knowledge-increasable and structure-extendible ability. The method helps to provide explanation of the transformation mechanism of human recognition system and understand the theory of global architecture of neural network.

Author-supplied keywords

  • exponential dually flat
  • hierarchical mixture-of-expert
  • information geometry
  • manifold
  • neural network

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • PUI: 36855995
  • SGR: 0038488771
  • SCOPUS: 2-s2.0-0038488771
  • ISBN: 0780374908


  • W A N G Hua

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free