Application of Hierarchical Temporal Memory Theory for Document Categorization

TL;DR

This paper explores the use of Hierarchical Temporal Memory (HTM) theory, inspired by the human neocortex, for automated document classification, employing the Spatial Pooler algorithm and Latent Semantic Indexing for feature extraction.

Contribution

It introduces a novel framework combining HTM with LSI for text classification, demonstrating competitive performance with existing machine learning methods.

Findings

HTM performs comparably to popular classifiers.

LSI effectively converts text into binary input for HTM.

Spatial Pooler creates overlapping patterns for similar texts.

Abstract

The current work intends to study the performance of the Hierarchical Temporal Memory(HTM) theory for automated classification of text as well as documents. HTM is a biologically inspired theory based on the working principles of the human neocortex. The current study intends to provide an alternative framework for document categorization using the Spatial Pooler learning algorithm in the HTM Theory. As HTM accepts only a stream of binary data as input, Latent Semantic Indexing(LSI) technique is used for extracting the top features from the input and converting them into binary format. The Spatial Pooler algorithm converts the binary input into sparse patterns with similar input text having overlapping spatial patterns making it easy for classifying the patterns into categories. The results obtained prove that HTM theory, although is in its nascent stages, performs at par with most of the popular machine learning based classifiers.