Stochastic Implementation of the Activation Function for Artificial Neural Networks

被引：0

作者：

Yeo, Injune ^{[1
]}

Gi, Sang-gyun ^{[1
]}

Lee, Byung-geun ^{[1
]}

Chu, Myonglae ^{[2
]}

机构：

[1] Gwangju Inst Sci & Technol, Sch Elect Engn & Comp Sci, Gwangju, South Korea

[2] IMEC, Interuniv Microelect Ctr, Imager SoC Team, Leuven, Belgium

来源：

PROCEEDINGS OF 2016 IEEE BIOMEDICAL CIRCUITS AND SYSTEMS CONFERENCE (BIOCAS) | 2016年

基金：

新加坡国家研究基金会;

关键词：

Artificial neural network; nonlinear activation function; neuromorphic; stochastic neuron; ananlog computing element;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

One of the key elements in an artificial neural networks (ANNs) is the activation function (AF), that converts the weighted sum of a neuron's input into a probability of firing rate. The hardware implementation of the AF requires complicated circuits and involves a considerable amount of power dissipation. This renders the integration of a number of neurons onto a single chip difficult. This paper presents circuit techniques for realizing four different types of AFs, such as the step, identity, rectified-linear unit (ReLU), and the sigmoid, based on stochastic computing. The proposed AF circuits are simpler and consume considerably lesser power than the existing ones. A handwritten digit recognition system employing the AF circuits has been simulated for verifying the effectiveness of the techniques.

引用

页码：440 / 443

页数：4