Feature extraction without learning in an analog spatial pooler memristive-CMOS circuit design of hierarchical temporal memory

Olga Krestinskaya, Alex Pappachen James

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Hierarchical temporal memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalAnalog Integrated Circuits and Signal Processing
DOIs
Publication statusAccepted/In press - Mar 15 2018

Fingerprint

Feature extraction
Data storage equipment
Networks (circuits)
Face recognition
Computer hardware
Hardware

Keywords

  • Analog circuits
  • Hierarchical temporal memory
  • Memristors
  • Rule based approach
  • Spatial Pooler

ASJC Scopus subject areas

  • Signal Processing
  • Hardware and Architecture
  • Surfaces, Coatings and Films

Cite this

@article{3da19033c65e402881b93430c2ea1998,
title = "Feature extraction without learning in an analog spatial pooler memristive-CMOS circuit design of hierarchical temporal memory",
abstract = "Hierarchical temporal memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.",
keywords = "Analog circuits, Hierarchical temporal memory, Memristors, Rule based approach, Spatial Pooler",
author = "Olga Krestinskaya and James, {Alex Pappachen}",
year = "2018",
month = "3",
day = "15",
doi = "10.1007/s10470-018-1161-1",
language = "English",
pages = "1--9",
journal = "Analog Integrated Circuits and Signal Processing",
issn = "0925-1030",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Feature extraction without learning in an analog spatial pooler memristive-CMOS circuit design of hierarchical temporal memory

AU - Krestinskaya, Olga

AU - James, Alex Pappachen

PY - 2018/3/15

Y1 - 2018/3/15

N2 - Hierarchical temporal memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.

AB - Hierarchical temporal memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.

KW - Analog circuits

KW - Hierarchical temporal memory

KW - Memristors

KW - Rule based approach

KW - Spatial Pooler

UR - http://www.scopus.com/inward/record.url?scp=85044018287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044018287&partnerID=8YFLogxK

U2 - 10.1007/s10470-018-1161-1

DO - 10.1007/s10470-018-1161-1

M3 - Article

AN - SCOPUS:85044018287

SP - 1

EP - 9

JO - Analog Integrated Circuits and Signal Processing

JF - Analog Integrated Circuits and Signal Processing

SN - 0925-1030

ER -