DS4NN: Direct training of deep spiking neural networks with single spike-based temporal coding

Backpropagation is the foremost prevalent and common algorithm for training conventional neural networks with deep construction. Here we propose DS4NN, temporal backpropagation for deep spiking neural networks with one spike per neuron. We consider a convolutional spiking neural network consisting o...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Maryam Mirsadeghi, Majid Shalchian, Saeed Reza Kheradpisheh
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	Amirkabir University of Technology 2023-12-01
Цуврал:	AUT Journal of Electrical Engineering
Нөхцлүүд:	deep spiking neural network temporal backpropagation single spike-based coding supervised learning integrate-and-fire neuron model
Онлайн хандалт:	https://eej.aut.ac.ir/article_5080_802cb5a6c14d7e84c5eb6168b526f23a.pdf
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!