Feature extraction without learning in an analog Spatial Pooler memristive-CMOS circuit design of Hierarchical Temporal Memory

TL;DR

This paper presents a deterministic feature encoding method for Hierarchical Temporal Memory that preserves input sparsity and improves face recognition performance, along with a memristive-CMOS hardware implementation.

Contribution

It introduces a novel deterministic initialization method for HTM that links weights to input data and maintains natural sparsity, along with hardware design and performance comparison.

Findings

Outperforms traditional HTM in face recognition tasks

Preserves input sparsity through deterministic weight assignment

Provides hardware implementation with memristive-CMOS circuits

Abstract

Hierarchical Temporal Memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.