• Cite Icon2
  • https://doi.org/10.5121/ijaia.2020.11407Copy DOI Icon

Scaling the HTM Spatial Pooler

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The Hierarchical Temporal Memory Cortical Learning Algorithm (HTM CLA) is a theory and machine learning technology that aims to capture cortical algorithm of the neocortex. Inspired by the biological functioning of the neocortex, it provides a theoretical framework, which helps to better understand how the cortical algorithm inside of the brain might work. It organizes populations of neurons in column-like units, crossing several layers such that the units are connected into structures called regions (areas). Areas and columns are hierarchically organized and can further be connected into more complex networks, which implement higher cognitive capabilities like invariant representations. Columns inside of layers are specialized on learning of spatial patterns and sequences. This work targets specifically spatial pattern learning algorithm called Spatial Pooler. A complex topology and high number of neurons used in this algorithm, require more computing power than even a single machine with multiple cores or a GPUs could provide. This work aims to improve the HTM CLA Spatial Pooler by enabling it to run in the distributed environment on multiple physical machines by using the Actor Programming Model. The proposed model is based on a mathematical theory and computation model, which targets massive concurrency. Using this model drives different reasoning about concurrent execution and enables flexible distribution of parallel cortical computation logic across multiple physical nodes. This work is the first one about the parallel HTM Spatial Pooler on multiple physical nodes with named computational model. With the increasing popularity of cloud computing and server less architectures, it is the first step towards proposing interconnected independent HTM CLA units in an elastic cognitive network. Thereby it can provide an alternative to deep neuronal networks, with theoretically unlimited scale in a distributed cloud environment.

Similar Papers
  • Conference Article
  • Citations1

The Parallel HTM Spatial Pooler with Actor Model

  • Jun 13, 2020
  • Damir Dobric +3
  • Research Article
  • Citations21

Spatial pattern learning in rats: Control by an iterative pattern.

  • Jan 01, 2001
  • Journal of Experimental Psychology: Animal Behavior Processes
  • Michael F Brown +2
  • Research Article
  • Citations16

Sex differences in spatial search and pattern learning in the rat

  • Sep 01, 1999
  • Psychobiology
  • Brian K Lebowitz +1
  • Research Article
  • Citations16

Deep learning in automated text classification: a case study using toxicological abstracts

  • Feb 27, 2020
  • Environment Systems and Decisions
  • Arun Varghese +2
  • Conference Article

ST-GRIT: Spatio-Temporal Graph Transformer For Internal Ice Layer Thickness Prediction

  • Sep 14, 2025
  • Zesheng Liu +1
  • Book Chapter
  • Citations1

A Distributed and Parallel Component Architecture for Stream-Oriented Applications

  • Jan 01, 2004
  • P Barthelmess +1
  • Research Article
  • Citations1

Invariant representations in deep learning for optoacoustic imaging

  • May 01, 2023
  • Review of Scientific Instruments
  • M Vera +2
  • PDF
  • Research Article
  • Citations14

Distributed detection of sequential anomalies in univariate time series

  • Mar 25, 2021
  • The VLDB Journal
  • Johannes Schneider +2
  • Abstract

Prolactin induces excessive grooming in the rat

  • Mar 01, 1981
  • Behavioural Brain Research
  • F Drago +3
  • PDF
  • Research Article
  • Citations1

Models and methods for analyzing complex networks and social network structures

  • Apr 07, 2023
  • Russian Technological Journal
  • Juю P Perova +2
  • Conference Article
  • Citations51

Coordinated power management of periodic real-time tasks on chip multiprocessors

  • Aug 01, 2010
  • Vinay Devadas +1
  • Research Article

IMVoteRank: Identifying multiple influential nodes in complex networks based on an improved voting model

  • Jan 01, 2025
  • Acta Physica Sinica
  • Li Shangjie +4
  • Research Article
  • Citations10

Machine learning is changing osteoporosis detection: an integrative review.

  • Jun 10, 2025
  • Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA
  • Yuji Zhang +8
  • PDF
  • Research Article
  • Citations3

A Hybrid Ensemble Model for Corporate Bankruptcy Prediction Based on Feature Engineering Method

  • Jan 01, 2019
  • International Journal of Information and Communication Sciences
  • Xiaoxia Wu +3
  • Research Article
  • Citations11

Distance Metric Learning for Radio Fingerprinting Localization

  • Jul 28, 2020
  • Expert Systems with Applications
  • Siqi Bai +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.