Rxivist logo

The HTM Spatial Pooler: a neocortical algorithm for online sparse distributed coding

By Yuwei Cui, Subutai Ahmad, Jeff Hawkins

Posted 02 Nov 2016
bioRxiv DOI: 10.1101/085035 (published DOI: 10.3389/fncom.2017.00111)

Hierarchical temporal memory (HTM) provides a theoretical framework that models several key computational principles of the neocortex. In this paper we analyze an important component of HTM, the HTM spatial pooler (SP). The SP models how neurons learn feedforward connections and form efficient representations of the input. It converts arbitrary binary input patterns into sparse distributed representations (SDRs) using a combination of competitive Hebbian learning rules and homeostatic excitability control. We describe a number of key properties of the spatial pooler, including fast adaptation to changing input statistics, improved noise robustness through learning, efficient use of cells and robustness to cell death. In order to quantify these properties we develop a set of metrics that can be directly computed from the spatial pooler outputs. We show how the properties are met using these metrics and targeted artificial simulations. We then demonstrate the value of the spatial pooler in a complete end-to-end real-world HTM system. We discuss the relationship with neuroscience and previous studies of sparse coding. The HTM spatial pooler represents a neurally inspired algorithm for learning sparse representations from noisy data streams in an online fashion.

Download data

  • Downloaded 5,691 times
  • Download rankings, all-time:
    • Site-wide: 1,555
    • In neuroscience: 80
  • Year to date:
    • Site-wide: 31,736
  • Since beginning of last month:
    • Site-wide: 31,736

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)