Neural networks and physical systems with emergent collective computational abilities.

TLDR

Computational abilities can emerge from large collections of simple components, and content‑addressable memory is represented by the phase‑space flow of such systems. The authors present a neurobiology‑inspired model that can be implemented on integrated circuits. The model evolves asynchronously in parallel, using a simple algorithm that updates the system state. The model yields robust content‑addressable memory from any sufficiently large subpart, and also shows emergent generalization, familiarity recognition, categorization, error correction, time‑sequence retention, and insensitivity to device failures.

Abstract

Computational properties of use of biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equivalent components (or neurons). The physical meaning of content-addressable memory is described by an appropriate phase space flow of the state of a system. A model of such a system is given, based on aspects of neurobiology but readily adapted to integrated circuits. The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. The algorithm for the time evolution of the state of the system is based on asynchronous parallel processing. Additional emergent collective properties include some capacity for generalization, familiarity recognition, categorization, error correction, and time sequence retention. The collective properties are only weakly sensitive to details of the modeling or the failure of individual devices.