WLC_Learning.pdf (6.02 MB)
Fast social-like learning of complex behaviors based on motor motifs
journal contribution
posted on 2018-07-27, 15:18 authored by Carlos Calvo Tapia, Ivan Y. Tyukin, Valeri A. MakarovSocial 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), 052308Author affiliation
/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of MathematicsVersion
- AM (Accepted Manuscript)
Published in
Physical Review EPublisher
American Physical Societyissn
2470-0045eissn
2470-0053Copyright date
2018Available date
2018-07-27Publisher DOI
Publisher version
https://journals.aps.org/pre/abstract/10.1103/PhysRevE.97.052308Language
enAdministrator link
Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC