期刊
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
卷 2016, 期 -, 页码 -出版社
HINDAWI LTD
DOI: 10.1155/2016/3917892
关键词
-
资金
- Spanish Ministry of Economy and Competitiveness (MINECO)
- Regional European Development Funds (FEDER)
- Comunitat Autonoma de les Illes Balears [TEC2011-23113, TEC2014-56244-R, AA/EE018/2012]
- European Social Fund (ESF) [FPI/1513/2012]
- Govern de les Illes Balears (Conselleria d'Educacio, Cultura i Universitats)
Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据