AnalogHTM: Memristive Spatial Pooler Learning with Backpropagation

Olga Krestinskaya, Alex Pappachen James

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Spatial pooler is responsible for feature extraction in Hierarchical Temporal Memory (HTM). In this paper, we present analog backpropagation learning circuits integrated to the memristive circuit design of spatial pooler. Using 0.18μm CMOS technology and TiOx memristor models, the maximum on-chip area and power consumption of the proposed design are 8335.074μm2 and 51.55mW, respectively. The system is tested for a face recognition problem AR face database achieving a recognition accuracy of 90%.

Original languageEnglish
Title of host publicationProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages262-266
Number of pages5
ISBN (Electronic)9781538678848
DOIs
Publication statusPublished - Mar 1 2019
Event1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 - Hsinchu, Taiwan
Duration: Mar 18 2019Mar 20 2019

Publication series

NameProceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

Conference

Conference1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019
CountryTaiwan
CityHsinchu
Period3/18/193/20/19

Fingerprint

Backpropagation
Memristors
Face recognition
Integrated circuits
Feature extraction
Electric power utilization
Data storage equipment
Networks (circuits)

Keywords

  • backpropagation
  • HTM
  • learning
  • memristor
  • Spatial Pooler

ASJC Scopus subject areas

  • Artificial Intelligence
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Krestinskaya, O., & James, A. P. (2019). AnalogHTM: Memristive Spatial Pooler Learning with Backpropagation. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019 (pp. 262-266). [8771628] (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICAS.2019.8771628

AnalogHTM : Memristive Spatial Pooler Learning with Backpropagation. / Krestinskaya, Olga; James, Alex Pappachen.

Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 262-266 8771628 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krestinskaya, O & James, AP 2019, AnalogHTM: Memristive Spatial Pooler Learning with Backpropagation. in Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019., 8771628, Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 262-266, 1st IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, Hsinchu, Taiwan, 3/18/19. https://doi.org/10.1109/AICAS.2019.8771628
Krestinskaya O, James AP. AnalogHTM: Memristive Spatial Pooler Learning with Backpropagation. In Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 262-266. 8771628. (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019). https://doi.org/10.1109/AICAS.2019.8771628
Krestinskaya, Olga ; James, Alex Pappachen. / AnalogHTM : Memristive Spatial Pooler Learning with Backpropagation. Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 262-266 (Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019).
@inproceedings{7acd7f948ef34061a21c74f51476e7a6,
title = "AnalogHTM: Memristive Spatial Pooler Learning with Backpropagation",
abstract = "Spatial pooler is responsible for feature extraction in Hierarchical Temporal Memory (HTM). In this paper, we present analog backpropagation learning circuits integrated to the memristive circuit design of spatial pooler. Using 0.18μm CMOS technology and TiOx memristor models, the maximum on-chip area and power consumption of the proposed design are 8335.074μm2 and 51.55mW, respectively. The system is tested for a face recognition problem AR face database achieving a recognition accuracy of 90{\%}.",
keywords = "backpropagation, HTM, learning, memristor, Spatial Pooler",
author = "Olga Krestinskaya and James, {Alex Pappachen}",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/AICAS.2019.8771628",
language = "English",
series = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "262--266",
booktitle = "Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019",
address = "United States",

}

TY - GEN

T1 - AnalogHTM

T2 - Memristive Spatial Pooler Learning with Backpropagation

AU - Krestinskaya, Olga

AU - James, Alex Pappachen

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Spatial pooler is responsible for feature extraction in Hierarchical Temporal Memory (HTM). In this paper, we present analog backpropagation learning circuits integrated to the memristive circuit design of spatial pooler. Using 0.18μm CMOS technology and TiOx memristor models, the maximum on-chip area and power consumption of the proposed design are 8335.074μm2 and 51.55mW, respectively. The system is tested for a face recognition problem AR face database achieving a recognition accuracy of 90%.

AB - Spatial pooler is responsible for feature extraction in Hierarchical Temporal Memory (HTM). In this paper, we present analog backpropagation learning circuits integrated to the memristive circuit design of spatial pooler. Using 0.18μm CMOS technology and TiOx memristor models, the maximum on-chip area and power consumption of the proposed design are 8335.074μm2 and 51.55mW, respectively. The system is tested for a face recognition problem AR face database achieving a recognition accuracy of 90%.

KW - backpropagation

KW - HTM

KW - learning

KW - memristor

KW - Spatial Pooler

UR - http://www.scopus.com/inward/record.url?scp=85070439189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070439189&partnerID=8YFLogxK

U2 - 10.1109/AICAS.2019.8771628

DO - 10.1109/AICAS.2019.8771628

M3 - Conference contribution

AN - SCOPUS:85070439189

T3 - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

SP - 262

EP - 266

BT - Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -