An Effective Algorithm of Restricted Boltzmann Machine Based on Momentum Method

SHEN Hui-hui; LI Hong-wei

doi:10.3969/j.issn.0372-2112.2019.01.023

您当前的位置：

首页 >

文章列表页 >

An Effective Algorithm of Restricted Boltzmann Machine Based on Momentum Method

更新时间：2025-07-16

- An Effective Algorithm of Restricted Boltzmann Machine Based on Momentum Method
- Acta Electronica Sinica Vol. 47, Issue 1, Pages: 176-182(2019)
- 作者机构：
  
  1. 中国地质大学数理学院,湖北,武汉,430074
  2. 湖北经济学院信息管理与统计学院,湖北,武汉,430205
  3. 中国地质大学(武汉)地球内部多尺度成像湖北省重点实验室,湖北,武汉,430074
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2019.01.023
  CLC： TP391
- Published Online：25 January 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
SHEN Hui-hui, LI Hong-wei. An Effective Algorithm of Restricted Boltzmann Machine Based on Momentum Method[J]. Acta Electronica Sinica, 2019, 47(1): 176-182.
DOI：

SHEN Hui-hui, LI Hong-wei. An Effective Algorithm of Restricted Boltzmann Machine Based on Momentum Method[J]. Acta Electronica Sinica, 2019, 47(1): 176-182. DOI： 10.3969/j.issn.0372-2112.2019.01.023.

摘要

深度学习给模式识别与机器学习带来了巨大的变化，已成功应用于语言处理、图像处理、信号处理、商业经济等方面.受限玻尔兹曼机（Restricted Boltzmann Machine，RBM）是一个表示能力强、很好的生成模型，多个RBM堆叠而构成的深度信念网络模型（Deep Belief Nets，DBN）的学习时间会较长.为加快整个DBN网络的学习时间和提高分类效果，本文提出基于动量方法RBM的一种有效算法.该算法在RBM预训练阶段，结合梯度上升算法特点采取快速上升的动量方式；以及BP算法微调阶段，为了能精确的找到最优点，结合梯度下降算法特点，相应的引入缓慢下降式的动量项，即在梯度上升和梯度下降过程中都使用不同的动量方式.本文算法在MNIST手写数字体和CMU-PIE人脸数据库上进行了实验，结果表明，提出的改进算法能够有效地增强图像特征的表达能力，提高图像的分类效果和实验效率.

Abstract

Deep learning is bringing revolution to pattern recognition and machine learning

which has been successfully applied to language processing

image processing

signal processing

business economy and so on.Restricted Boltzmann machine (RBM) is a strong representation and generative mod el

however

the learning time of deep belief nets (DBN)

which consists of multiple stacking RBM

will be longer.In this paper

the improved momentum method is used not only in gradient ascent algorithm but also in gradient descent algorithm for both classification accuracy enhancement and training time decreasing.According to the characteristics of the gradient ascent algorithm

a rapidly ascending momentum method is used in the RBM pre-training phase

which greatly improves the speed of learning.According to the characteristics of the gradient descent algorithm

an improved slowly descending momentum term is also used in the fine-tuning stage to accurately find the best point.Through the recognition experiments on the MNIST dataset and CMU-PIE face dataset

the achieved results show that the improved momentum algorithm can effectively enhance the ability of image feature expression and improve both accuracy and computation efficiency.

关键词

Keywords

references

Views

279

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Algorithm Based on Modified Momentum Using Restricted Boltzmann Machine

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Differentially Private with Sparse and Smooth Self-Distillation

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

A Method for Enhancing the Quality of Decompressed Point Clouds Based on Attention-Fused Multi-Scale Features

Related Author

SHEN Hui-hui

LIU Guo-wu

FU Li-hua

LIU Zhi-hui

HUANG Yu-zhe

GUAN Yong-yuan

WEI Song-jie

ZHAO Deng-feng

Related Institution

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

School of Information, Renmin University of China

College of Information Engineering, Capital Normal University

School of Mathematical Science, Capital Normal University

Faculty of Software Technologics, Shanxi Agricultural University

⁰