Silicon spiking neurons for hardware implementation of extreme learning machines
Silicon spiking neurons for hardware implementation of extreme learning machines
复制标题
DOI：
10.1016/j.neucom.2012.01.042
复制
发表时间：
2013-02-15
期刊：
影响因子：
6
通讯作者：
Huang, Guang-Bin
中科院分区：
文献类型：
--
作者：
Basu, Arindam;Shuo, Sun;Huang, Guang-Bin
在本文中，我们提出了一种使用尖峰神经电路的极限学习机（ELM）的硅实现。描述了硅尖峰神经网络、神经元、突触和用于基于异步尖峰通信的“地址事件表示”(AER) 的主要组件。解释了使用该硬件实现 ELM 相对于其他单层前馈网络 (SLFN) 的优势。提出了使用这些电路有效实现 ELM 的几种可能架构，并讨论了它们对 ELM 性能的可能影响。 (C) 2012 Elsevier B.V. 保留所有权利。
In this paper, we propose a silicon implementation of extreme learning machines (ELM) using spiking neural circuits. The major components of a silicon spiking neural network, neuron, synapse and 'Address Event Representation' (AER) for asynchronous spike based communication, are described. The benefits of using this hardware to implement an ELM as opposed to other single layer feedforward networks (SLFN) are explained. Several possible architectures for efficient implementation of ELM using these circuits are presented and their possible impact on ELM performance is discussed. (C) 2012 Elsevier B.V. All rights reserved.