The detector principle of constructing artificial neural networks as an alternative to the connectionist paradigm
This addresses fundamental limitations in ANN design for AI researchers, but appears incremental as it builds on existing paradigms without proven broad impact.
The paper tackles the inadequacy of artificial neural networks (ANNs) compared to biological ones by proposing the detector principle as an alternative to the connectionist paradigm, which introduces a new neuron-detector model, counter training, and a novel architecture formation approach.
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.