Supervised learning in Spiking Neural Networks with Limited Precision: SNN/LP
This work addresses the challenge of efficient hardware realization for large-scale spiking neural networks, representing an incremental improvement in algorithm design.
The authors tackled the problem of supervised learning in Spiking Neural Networks by proposing SNN/LP, a novel algorithm using limited precision (3 bits) for synaptic weights and delays with genetic algorithm training, achieving results comparable or better than prior work and enabling hardware implementation.
A new supervised learning algorithm, SNN/LP, is proposed for Spiking Neural Networks. This novel algorithm uses limited precision for both synaptic weights and synaptic delays; 3 bits in each case. Also a genetic algorithm is used for the supervised training. The results are comparable or better than previously published work. The results are applicable to the realization of large scale hardware neural networks. One of the trained networks is implemented in programmable hardware.