The detector principle of constructing artificial neural networks as an alternative to the connectionist paradigm

TL;DR

This paper introduces the detector principle as a new approach to constructing artificial neural networks, addressing limitations of the traditional connectionist paradigm by focusing on neuron input signal binding and proposing novel models and training methods.

Contribution

It presents a new neuron-detector model, a counter training approach, and an alternative architecture formation method as a departure from traditional connectionist ANN design.

Findings

Proposes the detector principle as an alternative to connectionist models.

Introduces a new neuron-detector model based on input signal binding.

Suggests a novel training method called counter training.

Abstract

Artificial neural networks (ANN) are inadequate to biological neural networks. This inadequacy is manifested in the use of the obsolete model of the neuron and the connectionist paradigm of constructing ANN. The result of this inadequacy is the existence of many shortcomings of the ANN and the problems of their practical implementation. The alternative principle of ANN construction is proposed in the article. This principle was called the detector principle. The basis of the detector principle is the consideration of the binding property of the input signals of a neuron. A new model of the neuron-detector, a new approach to teaching ANN - counter training and a new approach to the formation of the ANN architecture are used in this principle.