• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >GeCo: Classification Restricted Boltzmann Machine Hardware for On-Chip Semisupervised Learning and Bayesian Inference
【24h】

GeCo: Classification Restricted Boltzmann Machine Hardware for On-Chip Semisupervised Learning and Bayesian Inference

机译：GeCo：片上半监督学习和贝叶斯推理的受限分类玻尔兹曼机器硬件

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

The probabilistic Bayesian inference of real-time input data is becoming more popular, and the importance of semisupervised learning is growing. We present a classification restricted Boltzmann machine (ClassRBM)-based hardware accelerator with on-chip semisupervised learning and Bayesian inference capability. ClassRBM is a specific type of Markov network that can perform classification tasks and reconstruct its input data. ClassRBM has several advantages in terms of hardware implementation compared to other backpropagation-based neural networks. However, its accuracy is relatively low compared to backpropagation-based learning. To improve the accuracy of ClassRBM, we propose the multi-neuron-per-class (multi-NPC) voting scheme. We also reveal that the contrastive divergence (CD) algorithm, which is commonly used to train RBM, shows poor performance in this multi-NPC ClassRBM. As an alternative, we propose an asymmetric contrastive divergence (ACD) training algorithm that improves the accuracy of multi-NPC ClassRBM. With the ACD learning algorithm, ClassRBM operates in the form of a combination of Markov Chain training and Bayesian inference. The experimental results on a field-programmable gate array (FPGA) board for a Modified National Institute of Standards and Technology data set confirm that the inference accuracy of the proposed ACD algorithm is 5.82% higher for a supervised learning case and 12.78% higher for a 1% labeled semisupervised learning case than the conventional CD algorithm. Also, the GeCo ver.2 hardware implemented on a Xilinx ZCU102 FPGA board was 349.04 times faster than the C simulation on CPU.
机译：实时输入数据的概率贝叶斯推理正变得越来越流行，并且半监督学习的重要性也在增长。我们提出了一种基于分类受限玻尔兹曼机（ClassRBM）的硬件加速器，具有片上半监督学习和贝叶斯推理能力。 ClassRBM是Markov网络的一种特殊类型，可以执行分类任务并重建其输入数据。与其他基于反向传播的神经网络相比，ClassRBM在硬件实现方面具有多个优势。但是，与基于反向传播的学习相比，其准确性相对较低。为了提高ClassRBM的准确性，我们提出了每类多神经元（multi-NPC）投票方案。我们还揭示了通常用于训练RBM的对比散度（CD）算法在此多NPC ClassRBM中显示出较差的性能。作为替代方案，我们提出了一种非对称对比散度（ACD）训练算法，该算法可提高multi-NPC ClassRBM的准确性。借助ACD学习算法，ClassRBM以Markov Chain训练和贝叶斯推理的组合形式运行。在美国国家标准与技术研究院数据集的现场可编程门阵列（FPGA）板上进行的实验结果证实，对于有监督的学习案例，所提出的ACD算法的推理精度高出5.82％，对于有监督的学习案例，其高出12.78％。与传统的CD算法相比，有1％的标签为半监督学习案例。此外，在Xilinx ZCU102 FPGA板上实现的GeCo ver.2硬件比在CPU上进行C仿真要快349.04倍。

著录项

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