|
This article is cited in 4 scientific papers (total in 4 papers)
NONLINEAR DYNAMICS AND NEUROSCIENCE
Dynamics of an artificial recurrent neural network for the problem of modeling a cognitive function
O. V. Maslennikov Institute of Applied Physics of the Russian Academy of Sciences, Nizhny Novgorod, Russia
Abstract:
The purpose of this work is to build an artificial recurrent neural network whose activity models a cognitive function relating to the comparison of two vibrotactile stimuli coming with a delay and to analyze dynamic mechanisms underlying its work. Methods of the work are machine learning, analysis of spatiotemporal dynamics and phase space. Results. Activity of the trained recurrent neural network models a cognitive function of the comparison of two stimuli with a delay. Model neurons exhibit mixed selectivity during the course of the task. In the multidimensional activity, the components are found each of which depends on a certain task parameter. Conclusion. The training of the artificial neural network to perform the funciton analogous to the experimentally observed process is accompanied by the emergence of dynamic properties of model neurons which are similar to those found in the experiment.
Keywords:
recurrent neural network, machine learning, cognitive neuroscience.
Received: 26.02.2021
Citation:
O. V. Maslennikov, “Dynamics of an artificial recurrent neural network for the problem of modeling a cognitive function”, Izvestiya VUZ. Applied Nonlinear Dynamics, 29:5 (2021), 799–811
Linking options:
https://www.mathnet.ru/eng/ivp447 https://www.mathnet.ru/eng/ivp/v29/i5/p799
|
Statistics & downloads: |
Abstract page: | 137 | Full-text PDF : | 52 |
|