Analog value associative memory using restricted Boltzmann machine

Yuichiro Tsutsui, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper, we propose an analog value associative memory using Restricted Boltzmann Machine (AVAM). Research on treating knowledge is becoming more and more important such as in natural language processing and computer vision fields. Associative memory plays an important role to store knowledge. First, we obtain distributed representation of words with analog values using word2vec. Then the obtained distributed representation is learned in the proposed AVAM. In the evaluation experiments, we found simple but very important phenomenon in word2vec method: almost all of the values in the generated vectors are small values. By applying traditional normalization method for each word vector, the performance of the proposed AVAM is largely improved. Detailed experimental evaluations are carried out to show superior performance of the proposed AVAM.

Original languageEnglish
Pages (from-to)60-66
Number of pages7
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume23
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Data storage equipment
Computer vision
Processing
Experiments

Keywords

  • Associative memory
  • Restricted Boltzmann Machine
  • Semantic network
  • Word2vec

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Analog value associative memory using restricted Boltzmann machine. / Tsutsui, Yuichiro; Hagiwara, Masafumi.

In: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 23, No. 1, 01.01.2019, p. 60-66.

Research output: Contribution to journalArticle

@article{58199e1d82a34cff81a00ae6cf7669ce,
title = "Analog value associative memory using restricted Boltzmann machine",
abstract = "In this paper, we propose an analog value associative memory using Restricted Boltzmann Machine (AVAM). Research on treating knowledge is becoming more and more important such as in natural language processing and computer vision fields. Associative memory plays an important role to store knowledge. First, we obtain distributed representation of words with analog values using word2vec. Then the obtained distributed representation is learned in the proposed AVAM. In the evaluation experiments, we found simple but very important phenomenon in word2vec method: almost all of the values in the generated vectors are small values. By applying traditional normalization method for each word vector, the performance of the proposed AVAM is largely improved. Detailed experimental evaluations are carried out to show superior performance of the proposed AVAM.",
keywords = "Associative memory, Restricted Boltzmann Machine, Semantic network, Word2vec",
author = "Yuichiro Tsutsui and Masafumi Hagiwara",
year = "2019",
month = "1",
day = "1",
doi = "10.20965/jaciii.2019.p0060",
language = "English",
volume = "23",
pages = "60--66",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "1",

}

TY - JOUR

T1 - Analog value associative memory using restricted Boltzmann machine

AU - Tsutsui, Yuichiro

AU - Hagiwara, Masafumi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we propose an analog value associative memory using Restricted Boltzmann Machine (AVAM). Research on treating knowledge is becoming more and more important such as in natural language processing and computer vision fields. Associative memory plays an important role to store knowledge. First, we obtain distributed representation of words with analog values using word2vec. Then the obtained distributed representation is learned in the proposed AVAM. In the evaluation experiments, we found simple but very important phenomenon in word2vec method: almost all of the values in the generated vectors are small values. By applying traditional normalization method for each word vector, the performance of the proposed AVAM is largely improved. Detailed experimental evaluations are carried out to show superior performance of the proposed AVAM.

AB - In this paper, we propose an analog value associative memory using Restricted Boltzmann Machine (AVAM). Research on treating knowledge is becoming more and more important such as in natural language processing and computer vision fields. Associative memory plays an important role to store knowledge. First, we obtain distributed representation of words with analog values using word2vec. Then the obtained distributed representation is learned in the proposed AVAM. In the evaluation experiments, we found simple but very important phenomenon in word2vec method: almost all of the values in the generated vectors are small values. By applying traditional normalization method for each word vector, the performance of the proposed AVAM is largely improved. Detailed experimental evaluations are carried out to show superior performance of the proposed AVAM.

KW - Associative memory

KW - Restricted Boltzmann Machine

KW - Semantic network

KW - Word2vec

UR - http://www.scopus.com/inward/record.url?scp=85060870796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060870796&partnerID=8YFLogxK

U2 - 10.20965/jaciii.2019.p0060

DO - 10.20965/jaciii.2019.p0060

M3 - Article

AN - SCOPUS:85060870796

VL - 23

SP - 60

EP - 66

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 1

ER -