Encoding Data for HTM Systems
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 0; 2025: 1.
6 papers.
- 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 98
- 2022Unpaired Image Translation via Vector Symbolic Architecturescited by 13
- 2023Neuronal Auditory Machine Intelligence (NEURO-AMI) In Perspectivecited by 1
- 2021Cloud Failure Prediction with Hierarchical Temporal Memory: An Empirical Assessmentcited by 0
- 2023C3S Micro-architectural Enhancement: Spike Encoder Block and Relaxing Gamma Clock (Asynchronous)cited by 0
- 2025Enhancing Biologically Inspired Hierarchical Temporal Memory with Hardware-Accelerated Reflex Memorycited by 0
- 2025Enhancing Biologically Inspired Hierarchical Temporal Memory with Hardware-Accelerated Reflex Memory1 Apr 2025
- 2023Neuronal Auditory Machine Intelligence (NEURO-AMI) In Perspective14 Oct 2023
- 2023C3S Micro-architectural Enhancement: Spike Encoder Block and Relaxing Gamma Clock (Asynchronous)26 Jun 2023
- 2022Unpaired Image Translation via Vector Symbolic Architectures6 Sep 2022
- 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations11 Nov 2021
- 2021Cloud Failure Prediction with Hierarchical Temporal Memory: An Empirical Assessment6 Oct 2021