NENCFeb 18, 2016

Encoding Data for HTM Systems

arXiv:1602.05925v173 citationsHas Code
Originality Synthesis-oriented
AI Analysis

This addresses the need for effective data encoding in biologically inspired AI systems, but it is incremental as it builds on existing encoders and frameworks.

The paper tackles the problem of encoding data for Hierarchical Temporal Memory (HTM) systems by describing how to use Sparse Distributed Representations (SDRs), explaining existing encoders from the NuPIC project, and discussing requirements for new data types, without providing specific numerical results.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes