Welcome to the InfoSci Platform
Reference Hub4
Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning

Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning

Etienne Dumesnil, Philippe-Olivier Beaulieu, Mounir Boukadoum
Copyright: © 2017 |Volume: 11 |Issue: 2 |Pages: 24
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781522511700|DOI: 10.4018/IJCINI.2017040101
Cite Article Cite Article

MLA

Dumesnil, Etienne, et al. "Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning." IJCINI vol.11, no.2 2017: pp.1-24. http://doi.org/10.4018/IJCINI.2017040101

APA

Dumesnil, E., Beaulieu, P., & Boukadoum, M. (2017). Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 11(2), 1-24. http://doi.org/10.4018/IJCINI.2017040101

Chicago

Dumesnil, Etienne, Philippe-Olivier Beaulieu, and Mounir Boukadoum. "Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 11, no.2: 1-24. http://doi.org/10.4018/IJCINI.2017040101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A bio-inspired robotic brain is presented where the same spiking neural network (SNN) can implement five variations of learning by conditioning (LC): classical conditioning (CC), and operant conditioning (OC) with positive/negative reinforcement/punishment. In all cases, the links between input stimuli, output actions, reinforcements and punishments are strengthened depending on the stability of the delays between them. To account for the parallel processing nature of neural networks, the SNN is implemented on a field-programmable gate array (FPGA), and the neural delays are extracted via an adaptation of the synapto-dendritic kernel adapting neuron (SKAN) model, for a low resource demanding FPGA implementation of the SNN. A custom robotic platform successfully tested the ability of the proposed architecture to implement the five LC behaviors. Hence, this work contributes to the engineering field by proposing a scalable low resource demanding architecture for adaptive systems, and the cognitive field by suggesting that both CC and OC can be modeled as a single cognitive architecture.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.