Encoding Data for HTM Systems

TL;DR

This paper explains how to encode various data types into Sparse Distributed Representations for Hierarchical Temporal Memory systems, highlighting existing encoders and guidelines for developing new ones.

Contribution

It provides a comprehensive overview of encoding techniques for HTM systems and discusses requirements for creating custom encoders.

Findings

Overview of existing encoders in NuPIC

Guidelines for designing new encoders

Discussion on encoding data for HTM systems

Abstract

Hierarchical Temporal Memory (HTM) is a biologically inspired machine intelligence technology that mimics the architecture and processes of the neocortex. In this white paper we describe how to encode data as Sparse Distributed Representations (SDRs) for use in HTM systems. We explain several existing encoders, which are available through the open source project called NuPIC, and we discuss requirements for creating encoders for new types of data.