A Digital Multiplier-less Neuromorphic Model for Learning a Context-Dependent Task

• Published in: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) pp. 123 - 127
• Main Authors: Asgari, Hajar, Maybodi, Babak Mazloom-Nezhad, Kreiser, Raphaela, Sandamirskaya, Yulia
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-08-2020
• Subjects: context-dependent task; Field programmable gate arrays; Hardware; Integrated circuit modeling; Neuromorphic engineering; Neuromorphics; Neurons; reinforcement learning; spiking neural networks; Synapses; Task analysis
• DOI: 10.1109/AICAS48895.2020.9073881

Highly efficient performance-resources trade-off of the biological brain is a motivation for research on neuromorphic computing. Neuromorphic engineers develop event-based spiking neural networks (SNNs) in hardware. Learning in SNNs is a challenging topic of current research. Reinforcement learning (RL) is a particularly promising learning paradigm, important for developing autonomous agents. In this paper, we propose a digital multiplier-less hardware implementation of an SNN with RL capability. The network is able to learn stimulus-response associations in a context-dependent learning task. Validated in a robotic experiment, the proposed model replicates the behavior in animal experiments and the respective computational model.