Restricted Boltzmann Machine with Multivalued Hidden Variables A Model Suppressing Over-Fitting

被引：7

作者：

Yokoyama, Yuuki ^{[1
]}

Katsumata, Tomu ^{[2
]}

Yasuda, Muneki ^{[2
]}

机构：

[1] ALBERT Inc, Tokyo, Japan

[2] Yamagata Univ, Grad Sch Sci & Engn, Yamagata, Japan

来源：

REVIEW OF SOCIONETWORK STRATEGIES | 2019年 / 13卷 / 02期

关键词：

Statistical machine learning; Restricted Boltzmann machine; Pattern recognition; Generalization; LEARNING ALGORITHM;

D O I：

10.1007/s12626-019-00042-4

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Generalization is one of the most important issues in machine learning problems. In this study, we consider generalization in restricted Boltzmann machines (RBMs). We propose an RBM with multivalued hidden variables, which is a simple extension of conventional RBMs. We demonstrate that the proposed model is better than the conventional model via numerical experiments for contrastive divergence learning with artificial data and a classification problem with MNIST.

引用

页码：253 / 266

页数：14

共 18 条

[1] BISHOP C. M., 2006, Pattern recognition and machine learning, DOI [DOI 10.1117/1.2819119, 10.1007/978-0-387-45528-0]
[2] Replica analysis of overfitting in regression models for time-to-event data
Coolen, A. C. C.
Barrett, J. E.
Paga, P.
Perez-Vicente, C. J.
[J]. JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL, 2017, 50 (37)
[3] Gabrie M., 2015, ADV NEURAL INFORM PR, P640
[4] Glorot X., 2010, P 13 INT C ART INT S, V9, P249
[5] Training products of experts by minimizing contrastive divergence
Hinton, GE
[J]. NEURAL COMPUTATION, 2002, 14 (08) : 1771 - 1800
[6] A fast learning algorithm for deep belief nets
Hinton, Geoffrey E.
Osindero, Simon
Teh, Yee-Whye
[J]. NEURAL COMPUTATION, 2006, 18 (07) : 1527 - 1554
[7] Kingma DP, 2014, ARXIV
[8] Larochelle H., 2008, P 25 INT C MACH LEAR, P536
[9] Larochelle H, 2012, J MACH LEARN RES, V13, P643
[10] Marlin B., 2010, J. Mach. Learn. Res., V9, P509

← 1 2 →