Effect of Spatial Pooler Initialization on Column Activity in Hierarchical Temporal Memory

Authors

  • Mackenzie Leake Scripps College
  • Liyu Xia University of Chicago
  • Kamil Rocki IBM Research
  • Wayne Imaino IBM Research

DOI:

https://doi.org/10.1609/aaai.v29i1.9734

Keywords:

Hierarchical Temporal Memory, HTM, Learning Algorithms, Machine Learning, Spatial Pooler

Abstract

In the Hierarchical Temporal Memory (HTM) paradigm the effect of overlap between inputs on the activation of columns in the spatial pooler is studied. Numerical results suggest that similar inputs are represented by similar sets of columns and dissimilar inputs are represented by dissimilar sets of columns. It is shown that the spatial pooler produces these results under certain conditions for the connectivity and proximal thresholds at initialization. Qualitative arguments about the learning dynamics of the spatial pooler are then discussed.

Downloads

Published

2015-03-04

How to Cite

Leake, M., Xia, L., Rocki, K., & Imaino, W. (2015). Effect of Spatial Pooler Initialization on Column Activity in Hierarchical Temporal Memory. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9734