Hybrid computation with an attractor neural network

Abstract

This paper discusses the properties of a controllable, flexible, hybrid parallel computing architecture that potentially merges pattern recognition and arithmetic. Humans perform integer arithmetic in a fundamentally different way than logic-based computers. Even though the human approach to arithmetic is slow and inaccurate for purely arithmetic computation, it can have substantial advantages when useful approximations ("intuition") are more valuable than high precision. Such a computational strategy may be particularly useful when computers based on nanocomponents become feasible because it offers a way to make use of the potential power of these massively parallel systems.