Categorization in fully connected multistate neural network models

Abstract

The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multistate patterns in a two level structure of ancestors and descendents (examples) are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q=3-state model and a Q=infinity-state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The categorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained.

Retrieval behavior and thermodynamic properties of symmetrically dilutedQ-Ising neural networks

“…The study of the effects of symmetric synaptic dilution may be extended to other problems that deal with associative memory, like the categorization problem as a classification task in Q-Ising networks [24]. This has been done recently for Q = 2 [25] and there is work in progress for general Q [26].…”