Improved HTM Spatial Pooler with Homeostatic Plasticity Control

Damir Dobric, Andreas Pech, Bogdan Ghita, Thomas Wennekers

2021

Abstract

Hierarchical Temporal Memory (HTM) - Spatial Pooler (SP) is a Learning Algorithm for learning of spatial patterns inspired by the neo-cortex. It is designed to learn the pattern in a few iteration steps and to generate the Sparse Distributed Representation (SDR) of the input. It encodes spatially similar inputs into the same or similar SDRs memorized as a population of active neurons organized in groups called micro-columns. Findings in this research show that produced SDRs can be forgotten during the training progress, which causes the SP to learn the same pattern again and converts into the new SDR. This work shows that instable learning behaviour of the SP is caused by the internal boosting algorithm inspired by the homeostatic plasticity mechanism. Previous findings in neurosciences show that this mechanism is only active during the development of new-born mammals and later deactivated or shifted from cortical layer L4, where the SP is supposed to be active. The same mechanism was used in this work. The SP algorithm was extended with the new homeostatic plasticity component that controls the boosting and deactivates it after entering the stable state. Results show that learned SDRs remain stable during the lifetime of the Spatial Pooler.

Paper Citation

in Harvard Style

Dobric D., Pech A., Ghita B. and Wennekers T. (2021). Improved HTM Spatial Pooler with Homeostatic Plasticity Control.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 98-106. DOI: 10.5220/0010314200980106

in Bibtex Style

@conference{icpram21,
author={Damir Dobric and Andreas Pech and Bogdan Ghita and Thomas Wennekers},
title={Improved HTM Spatial Pooler with Homeostatic Plasticity Control},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={98-106},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010314200980106},
isbn={978-989-758-486-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Improved HTM Spatial Pooler with Homeostatic Plasticity Control
SN - 978-989-758-486-2
AU - Dobric D.
AU - Pech A.
AU - Ghita B.
AU - Wennekers T.
PY - 2021
SP - 98
EP - 106
DO - 10.5220/0010314200980106