• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Accelerating Stochastic Random Projection Neural Networks
【24h】

Accelerating Stochastic Random Projection Neural Networks

机译：加速随机随机投影神经网络

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Artificial Neural Network (ANN), a computational model based on the biological neural networks, has a recent resurgence in machine intelligence with breakthrough results in pattern recognition, speech recognition, and mapping. This has led to a growing interest in designing dedicated hardware substrates for ANNs with a goal of achieving energy efficiency, high network connectivity and better computational capabilities that are typically not optimized in software ANN stack. Using stochastic computing is a natural choice to reduce the total system energy, where a signal is expressed through the statistical distribution of the logical values as a random bit stream. Generally, the accuracy of these systems is correlated with the stochastic bit stream length and requires long compute times.;In this work, a framework is proposed to accelerate the long compute times in stochastic ANNs. A GPU acceleration framework has been developed to validate two random projection networks to test the efficacy of these networks prior to custom hardware design. The networks are stochastic extreme learning machine, a supervised feed-forward neural network and stochastic echo state network, a recurrent neural network with online learning. The framework also provisions identifying optimal values for various network parameters like learning rate, number of hidden layers and stochastic number length. The proposed stochastic extreme learning machine design is validated for two standardized datasets, MNIST dataset and orthopedic dataset. The proposed stochastic echo state network is validated on the time series EEG dataset. The CPU models were developed for each of these networks to calculate the relative performance boost. The design knobs for performance boost include stochastic bit stream generation, activation function, reservoir layer and training unit of the networks. Proposed stochastic extreme learning machine and stochastic echo state network achieved a performance boost of 60.61x for Orthopedic dataset and 42.03x for EEG dataset with 2.;12 bit stream length when tested on an NvidiaGeForce1050 Ti.
机译：人工神经网络（ANN）是一种基于生物神经网络的计算模型，近年来在机器智能领域重新兴起，在模式识别，语音识别和映射方面取得了突破性的成果。这引起了人们对于设计用于ANN的专用硬件基板的兴趣日益浓厚，其目标是实现能源效率，高网络连接性和更好的计算能力，而这些通常在软件ANN堆栈中并未优化。使用随机计算是减少系统总能量的一种自然选择，其中通过逻辑值的统计分布将信号表示为随机位流。通常，这些系统的准确性与随机比特流的长度有关，并且需要较长的计算时间。在这项工作中，提出了一个框架来加快随机ANN中较长的计算时间。已经开发了GPU加速框架来验证两个随机投影网络，以在定制硬件设计之前测试这些网络的功效。这些网络是随机极限学习机，监督前馈神经网络和随机回声状态网络，具有在线学习功能的递归神经网络。该框架还规定了识别各种网络参数（例如学习率，隐藏层数和随机数长度）的最佳值。所提出的随机极限学习机设计已针对两个标准化数据集MNIST数据集和整形外科数据集进行了验证。在时间序列脑电数据集上验证了所提出的随机回波状态网络。针对每个网络开发了CPU模型，以计算相对性能提升。用于提高性能的设计旋钮包括随机位流生成，激活功能，存储层和网络的训练单元。当在NvidiaGeForce1050 Ti上进行测试时，建议的随机极限学习机和随机回波状态网络对矫形数据集的性能提高了60.61倍，对EEG数据集的性能提高了42.03x，流长度为2.; 12位。

著录项

  • 作者

    Ramakrishnan, Swathika.;

  • 作者单位

    Rochester Institute of Technology.;

  • 授予单位 Rochester Institute of Technology.;
  • 学科 Computer engineering.;Artificial intelligence.
  • 学位 M.S.
  • 年度 2017
  • 页码 78 p.
  • 总页数 78
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 公共建筑;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号