HTM theory

Yeldos Dauletkhanuly; Olga Krestinskaya; Alex Pappachen James

doi:10.1007/978-3-030-14524-8_13

HTM theory

Yeldos Dauletkhanuly, Olga Krestinskaya, Alex Pappachen James

Department of Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

This chapter presents the general background information about the Hierarchical Temporal Memory (HTM). HTM is a recently proposed cognitive learning algorithm that is intended to emulate the overall structural and functionality of the human neocortex responsible for the high-order functions such as cognition, learning and making predictions. The main properties of HTM is hierarchical structure, sparsity and modularity. HTM consists of two main parts: HTM Spatial Pooler (SP) and HTM Temporal Memory (TM). The HTM SP performs the encoding of the input data and produces sparse distributed representation (SDR) of the input pattern useful for visual data processing and classification tasks. The HTM TM detects the temporal changes in the input data and performs prediction making.

Original language	English
Title of host publication	Modeling and Optimization in Science and Technologies
Publisher	Springer Verlag
Pages	169-180
Number of pages	12
DOIs	https://doi.org/10.1007/978-3-030-14524-8_13
Publication status	Published - 2020

Publication series

Name	Modeling and Optimization in Science and Technologies
Volume	14
ISSN (Print)	2196-7326
ISSN (Electronic)	2196-7334

ASJC Scopus subject areas

Modelling and Simulation
Medical Assisting and Transcription
Applied Mathematics

Access to Document

10.1007/978-3-030-14524-8_13

Fingerprint Dive into the research topics of 'HTM theory'. Together they form a unique fingerprint.

Cite this

@inbook{f4e00b324cf14e7ab41c70f9dda44584,

title = "HTM theory",

abstract = "This chapter presents the general background information about the Hierarchical Temporal Memory (HTM). HTM is a recently proposed cognitive learning algorithm that is intended to emulate the overall structural and functionality of the human neocortex responsible for the high-order functions such as cognition, learning and making predictions. The main properties of HTM is hierarchical structure, sparsity and modularity. HTM consists of two main parts: HTM Spatial Pooler (SP) and HTM Temporal Memory (TM). The HTM SP performs the encoding of the input data and produces sparse distributed representation (SDR) of the input pattern useful for visual data processing and classification tasks. The HTM TM detects the temporal changes in the input data and performs prediction making.",

author = "Yeldos Dauletkhanuly and Olga Krestinskaya and James, {Alex Pappachen}",

year = "2020",

doi = "10.1007/978-3-030-14524-8_13",

language = "English",

series = "Modeling and Optimization in Science and Technologies",

publisher = "Springer Verlag",

pages = "169--180",

booktitle = "Modeling and Optimization in Science and Technologies",

address = "Germany",

}

TY - CHAP

T1 - HTM theory

AU - Dauletkhanuly, Yeldos

AU - Krestinskaya, Olga

AU - James, Alex Pappachen

PY - 2020

Y1 - 2020

N2 - This chapter presents the general background information about the Hierarchical Temporal Memory (HTM). HTM is a recently proposed cognitive learning algorithm that is intended to emulate the overall structural and functionality of the human neocortex responsible for the high-order functions such as cognition, learning and making predictions. The main properties of HTM is hierarchical structure, sparsity and modularity. HTM consists of two main parts: HTM Spatial Pooler (SP) and HTM Temporal Memory (TM). The HTM SP performs the encoding of the input data and produces sparse distributed representation (SDR) of the input pattern useful for visual data processing and classification tasks. The HTM TM detects the temporal changes in the input data and performs prediction making.

AB - This chapter presents the general background information about the Hierarchical Temporal Memory (HTM). HTM is a recently proposed cognitive learning algorithm that is intended to emulate the overall structural and functionality of the human neocortex responsible for the high-order functions such as cognition, learning and making predictions. The main properties of HTM is hierarchical structure, sparsity and modularity. HTM consists of two main parts: HTM Spatial Pooler (SP) and HTM Temporal Memory (TM). The HTM SP performs the encoding of the input data and produces sparse distributed representation (SDR) of the input pattern useful for visual data processing and classification tasks. The HTM TM detects the temporal changes in the input data and performs prediction making.

UR - http://www.scopus.com/inward/record.url?scp=85064736367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064736367&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-14524-8_13

DO - 10.1007/978-3-030-14524-8_13

M3 - Chapter

AN - SCOPUS:85064736367

T3 - Modeling and Optimization in Science and Technologies

SP - 169

EP - 180

BT - Modeling and Optimization in Science and Technologies

PB - Springer Verlag

ER -