×

“Live” neuron and optimal learning rule. (English) Zbl 0747.92003

Summary: A concept of the live unit as an automatic regulation system with a few admissible states areas in the space of states is considered. Energetic profit of oscillatory behavior consisting in the consecutive transitions of systems from one admissible states area to another is shown. It is stated that external disturbances cause the energy consumption of oscillatory systems to decrease.
On the basis of this concept and some neurophysiological data, the “live” energy-consuming nonlinear three-state neuron model is proposed and the existence of energy optimal generation frequency \(\nu_{opt}\) is proved. For the realization of tendency to \(\nu_{opt}\) the optimal learning rule is proposed, which provides unsupervised learning and interlinked short-term and long-term memories with forgetting. The model proposed explains the genesis of neural networks, is promising in the sense of network self-organization and allows to solve the problem of internal activity in the researches on artificial intelligence.

MSC:

92B20 Neural networks for/in biological studies, artificial life and related topics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Bauer ES (1935) Theoretical biology. VIEM, Moscow Leningrad (in Russian)
[2] Eccles JC (1964) The physiology of synapses. Academic Press, New York
[3] Erlanger J, Gasser HS (1937) Electrical sign of nervous activity. University of Pennsylvania Press, Philadelphia
[4] Gilliatt RW, Willison RG (1962) Refracterness and supernormality in human peripheral nerve. J Physiol 161:29–30
[5] Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. PNAS USA 79:2554–2558 · Zbl 1369.92007 · doi:10.1073/pnas.79.8.2554
[6] Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. PNAS USA 81:3088–3092 · Zbl 1371.92015 · doi:10.1073/pnas.81.10.3088
[7] Widrow B (1973) Generalization and information storage in networks of Adaline neurons. In: Self-organizing systems. McGraw-Hill, New York
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.