High accuracy implementation of Adaptive Exponential integrated and fire neuron model
Proceedings of the International Joint Conference on Neural Networks
Adaptive Exponential integrated and fire model (AdEx), FPGA, High accuracy, Neuromorphic, Pipelining
It is expensive to simulate large-scale neural networks on hardware while ensuring a high resemblance to the original neurons' behavior. This paper introduces a novel technique to facilitate digital implementation and computer simulation of neuron models that contain an exponential term. This technique is applied to a biologically realistic neuron model called Adaptive Exponential integrated and fire (AdEx). Hardware synthesis and physical implementations show that the resulting model can reproduce precise neural behavior with high performance and considerably lower implementation costs compared with the original AdEx model.
Makhlooghpour, Aliasghar; Soleimani, Hamid; Ahmadi, Arash; Zwolinski, Mark; and Saif, Mehrdad. (2016). High accuracy implementation of Adaptive Exponential integrated and fire neuron model. Proceedings of the International Joint Conference on Neural Networks, 2016-October, 192-197.