Menu
Research Papers
Thu, Feb 18, 2016
Encoding Data for HTM Systems
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.
AUTHORS:
Scott Purdy
PUBLICATION:
Research Paper
Tue, Jan 05, 2016
How Do Neurons Operate on Sparse Distributed Representations? A Mathematical Theory of Sparsity, Neurons and Active Dendrites
This paper describes a mathematical model for quantifying the benefits and limitations of sparse representations in neurons and cortical networks.
AUTHORS:
Subutai Ahmad and Jeff Hawkins
PUBLICATION:
Preprint of journal submission
Mon, Oct 12, 2015
Evaluating Real-time Anomaly Detection Algorithms – the Numenta Anomaly Benchmark
14th IEEE ICMLA 2015 – This paper discusses how we should think about anomaly detection for streaming applications. It introduces a new open-source benchmark for detecting anomalies in real-time, time-series data.
AUTHORS:
Alexander Lavin and Subutai Ahmad
PUBLICATION:
Published conference paper
Fri, May 08, 2015
Porting HTM Models to the Heidelberg Neuromorphic Computing Platform
Recently there has been much interest in building custom hardware implementations of HTM systems. This paper discusses one such scenario, and shows how to port HTM algorithms to analog hardware platforms such as the one developed by the Human Brain Project.
AUTHORS:
Sebastian Billaudelle and Subutai Ahmad
PUBLICATION:
Research Paper
Wed, Mar 25, 2015
Properties of Sparse Distributed Representations and their Application To Hierarchical Temporal Memory
An earlier version of the above submission, this paper applies our mathematical model of sparse representations to practical HTM systems.
AUTHORS:
Subutai Ahmad and Jeff Hawkins
PUBLICATION:
Research Paper
Mon, Sep 12, 2011
Hierarchical Temporal Memory (HTM) Whitepaper
There have been changes in our thinking, in algorithm implementation, in terminology and in other areas since the HTM whitepaper was written, rendering part of this paper obsolete. Much of this paper has been replaced by BAMI and the current white papers.
AUTHORS:
Jeff Hawkins
PUBLICATION:
Whitepaper