An introduction to computing with neural nets

TLDR

Artificial neural networks have long been studied for speech and image recognition, comprising parallel nonlinear nodes connected by adaptable weights, and have recently resurged thanks to new topologies, algorithms, and analog VLSI techniques that exploit massive parallelism. The paper introduces six key neural net models for pattern classification and emphasizes how existing classification and clustering algorithms can be implemented with simple neuron‑like components. The authors review these six models and illustrate how classification and clustering algorithms can be executed using simple neuron‑like components. Single‑layer nets can implement Gaussian maximum‑likelihood and optimum minimum‑error classifiers for noisy binary patterns, while three‑layer feed‑forward nets can generate decision regions for any classification algorithm.

Abstract

Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.