Self-organization of day cycle and hierarchical associative memory in “live” neural network

✍ Scribed by L. B. Emelyanov-Yaroslavsky; V. I. Potapov

• Publisher: Springer-Verlag
• Year: 1992
• Tongue: English
• Weight: 820 KB
• Volume: 67
• Category: Article
• ISSN: 0340-1200
• DOI: 10.1007/bf00201804

✦ Synopsis

The "live" neural network model is proposed on the basis of "live" neuron model and optimal learning rule. By means of numerical simulation the initial stages of neural network self-organization have been shown: (1) the formation of two activity forms, which are identified with sleep and awaking, and (2) the self-organization of hierarchical associative memory when feeding a receptor excitation to the neural network. The energetic profit of self-organization is demonstrated. The formation of neural ensembles, playing the role of generalized neurons, is obtained. the connected groups of neurons (mutual aid groups -MAG's), which don't contain inhibitory links inside and have variable composition.

We consider that the constraints play the main role in the development of neural network, and by reasonable choice of constraints one can reach self-organization of various functions of the neural network, including intelligent functions. Therefore the second purpose of this work was to demonstrate the selforganization of hierarchical associative memory at some selected constraints, which don't contradict to the neurophysiological data.