Toward Scalable, Efficient, and Accurate Deep Spiking Neural Networks With Backward Residual Connections, Stochastic Softmax, and Hybridization

Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on supervised (conversion, spike-based gradient descent) and unsupervised (spike timing dependent plasticity) training meth...

Повний опис

Бібліографічні деталі

Автори:	Priyadarshini Panda, Sai Aparna Aketi, Kaushik Roy
Формат:	Artigo
Мова:	Inglês
Опубліковано:	Frontiers Media S.A. 2020-06-01
Серія:	Frontiers in Neuroscience
Предмети:	spiking neural networks energy-efficiency backward residual connection stochastic softmax hybridization improved accuracy
Онлайн доступ:	https://www.frontiersin.org/article/10.3389/fnins.2020.00653/full
Теги:	Додати тег Немає тегів, Будьте першим, хто поставить тег для цього запису!