Information Capacity of a Hierarchical Neural Network

1998/09/07 by David Renato Carreta Dominguez
Physics and Astronomy · #cond-mat.stat-mech

paper · pdf

published as Phys.Rev.E 58 (1998) October · 5 pages, 4 figures

arxiv created 1998/09/07 · arxiv updated 2009/11/30

Abstract

The information conveyed by a hierarchical attractor neural network is examined. The network learns sets of correlated patterns (the examples) in the lowest level of the hierarchical tree and can categorize them at the upper levels. A way to measure the non-extensive information content of the examples is formulated. Curves showing the transition from a large retrieval information to a large categorization information behavior, when the number of examples increase, are displayed. The conditions for the maximal information are given as functions of the correlation between examples and the load of concepts. Numerical simulations support the analytical results.

Related

• An attractor neural network architecture with an ultra high information capacity: numerical results
• Information and Topology in Attractor Neural Network
• Structured Information in Metric Neural Networks
• Neural Network Capacity for Multilevel Inputs
• Dynamical Neural Network: Information and Topology