Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning
| Autor: | Mounir Boukadoum, Philippe-Olivier Beaulieu, Etienne Dumesnil |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Spiking neural network
Artificial neural network Computer science business.industry 020208 electrical & electronic engineering Classical conditioning 02 engineering and technology Cognitive architecture Human-Computer Interaction 03 medical and health sciences 0302 clinical medicine Artificial Intelligence Adaptive system 0202 electrical engineering electronic engineering information engineering Reinforcement learning Operant conditioning Artificial intelligence Reinforcement business 030217 neurology & neurosurgery Software |
| Zdroj: | International Journal of Cognitive Informatics and Natural Intelligence. 11:1-24 |
| ISSN: | 1557-3966 1557-3958 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|