WLC_Learning.pdf (6.02 MB)
Download file

Fast social-like learning of complex behaviors based on motor motifs

Download (6.02 MB)
journal contribution
posted on 27.07.2018, 15:18 by Carlos Calvo Tapia, Ivan Y. Tyukin, Valeri A. Makarov
Social learning is widely observed in many species. Less experienced agents copy successful behaviors exhibited by more experienced individuals. Nevertheless, the dynamical mechanisms behind this process remain largely unknown. Here we assume that a complex behavior can be decomposed into a sequence of n motor motifs. Then a neural network capable of activating motor motifs in a given sequence can drive an agent. To account for (n-1)! possible sequences of motifs in a neural network, we employ the winnerless competition approach. We then consider a teacher-learner situation: one agent exhibits a complex movement, while another one aims at mimicking the teacher's behavior. Despite the huge variety of possible motif sequences we show that the learner, equipped with the provided learning model, can rewire "on the fly" its synaptic couplings in no more than (n-1) learning cycles and converge exponentially to the durations of the teacher's motifs. We validate the learning model on mobile robots. Experimental results show that the learner is indeed capable of copying the teacher's behavior composed of six motor motifs in a few learning cycles. The reported mechanism of learning is general and can be used for replicating different functions, including, for example, sound patterns or speech.

Funding

This work has been supported by the Russian Science Foundation under Project No. 15-12-10018 (the problem statement and theoretical development) and by the Spanish Ministry of Economy and Competitiveness under Grant No. FIS2014-57090-P.

History

Citation

Physical Review E, 2018, 97(5), 052308

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Mathematics

Version

AM (Accepted Manuscript)

Published in

Physical Review E

Publisher

American Physical Society

issn

2470-0045

eissn

2470-0053

Copyright date

2018

Available date

27/07/2018

Publisher version

https://journals.aps.org/pre/abstract/10.1103/PhysRevE.97.052308

Language

en

Usage metrics

Categories

Keywords

Exports