On the energy benefits of spiking deep neural networks: A case study
On the energy benefits of spiking deep neural networks: A case study
复制标题
关于脉冲深度神经网络的能源效益：案例研究
DOI：
10.1109/ijcnn.2016.7727303
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
K. Roy
中科院分区：
文献类型：
--
作者：
Bing Han;Abhronil Sengupta;K. Roy
深度学习神经网络已在大量的视觉处理任务中取得了成功，目前用于许多现实世界中的应用程序，例如图像搜索和语音识别等。但是，尽管在此类分类问题中达到了很高的精度，但它们涉及大量的计算资源。在过去的几年中，人工神经网络模型已演变为生物学现实和事件驱动的尖峰神经网络。最近的研究工作旨在开发机制，以将传统的深人造网络转换为尖刺网，其中神经元通过尖峰进行通信。但是，有限的研究提供了有关与非刺激性同行相比，深尖神经网所提供的特定能力，区域和能源益处的见解。在本文中，我们执行了一个案例研究，以实现MNIST数据集上的尖峰/非尖峰深网的硬件实现，并清楚地概述了以尖峰操作方式实现神经计算平台所涉及的设计前景。
Deep learning neural networks have achieved success in a large number of visual processing tasks and are currently utilized for many real-world applications like image search and speech recognition among others. However, in spite of achieving high accuracy in such classification problems, they involve significant computational resources. Over the past few years, artificial neural network models have evolved into the biologically realistic and event-driven spiking neural networks. Recent research efforts have been directed at developing mechanisms to convert traditional deep artificial nets to spiking nets where the neurons communicate by means of spikes. However, there have been limited studies providing insights on the specific power, area and energy benefits offered by deep spiking neural nets in comparison to their non-spiking counterparts. In this paper, we perform a case study for a hardware implementation of a spiking/non-spiking deep net on the MNIST dataset and clearly outline the design prospects involved in implementing neural computing platforms in the spiking mode of operation.