Image Based HTM Word Recognizer for Language processing [Article]

dc.contributor.authorJames, Alex Pappachen
dc.contributor.authorIrmanova, Aidana
dc.contributor.authorKrestinskaya, Olga
dc.date.accessioned2019-09-26T06:49:32Z
dc.date.available2019-09-26T06:49:32Z
dc.date.issued2019-11-29
dc.descriptionhttps://ieeexplore.ieee.org/document/8552117en_US
dc.description.abstractThe hardware implementation of neuro-inspired machine learning algorithms for near sensor processing on edge devices is an open problem. In this work, we propose a solution to written word recognition problem related to sequence learning tasks with images. Applying a theoretical framework of neocortex functionality as a sequence learning algorithm on a hardware implementation of Hierarchical Temporal Memory (HTM), we test the potential use of HTM in near-sensor on-chip natural language processing for text/symbol recognition.en_US
dc.identifier.citationIrmanova, A., Krestinskaya, O., & James, A. P. (2018). Image Based HTM Word Recognizer for Language Processing. In 2018 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia). IEEE. https://doi.org/10.1109/icce-asia.2018.8552117en_US
dc.identifier.isbn978-1-5386-5807-9
dc.identifier.other10.1109/ICCE-ASIA.2018.8552117
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/4261
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectHTM Word Recognizeren_US
dc.subjectLanguage Processingen_US
dc.subjectHierarchical Temporal Memoryen_US
dc.subjectResearch Subject Categories::TECHNOLOGYen_US
dc.titleImage Based HTM Word Recognizer for Language processing [Article]en_US
dc.typeArticleen_US
workflow.import.sourcescience

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Image Based HTM Word Recognizer for Language processing.pdf
Size:
1.22 MB
Format:
Adobe Portable Document Format
Description:
Article
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections