Numenta Logo

Research Papers

  1. A Theory of How Columns in the Neocortex Enable Learning the Structure of the World
    Jeff Hawkins, Subutai Ahmad & Yuwei Cui
    neuroscience, sensorimotor
    Published in Frontiers in Neural Circuits Journal2017/10/25

    This paper proposes a network model composed of columns and layers that performs robust object learning and recognition. The model introduces a new feature to cortical columns, location information, which is represented relative to the object being sensed. Pairing sensory features with locations is a requirement for modeling objects and therefore must occur somewhere in the neocortex. We propose it occurs in every column in every region.

  2. Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
    Jeff Hawkins & Subutai Ahmad
    neuroscience, sequence learning
    Published in Frontiers in Neural Circuits Journal2016/03/30

    Foundational paper describing core HTM theory for sequence memory and its relationship to the neocortex. Written with a neuroscience perspective, the paper explains why neurons need so many synapses and how networks of neurons can form a powerful sequence learning mechanism.

  3. The HTM Spatial Pooler—A Neocortical Algorithm for Online Sparse Distributed Coding
    Yuwei Cui, Subutai Ahmad & Jeff Hawkins
    neuroscience, sparse distributed representations
    Published in Frontiers in Neuroscience2017/11/29

    This paper describes an important component of HTM, the HTM spatial pooler, which is a neurally inspired algorithm that learns sparse distributed representations online. Written from a neuroscience perspective, the paper demonstrates key computational properties of HTM spatial pooler.

  4. Unsupervised Real-Time Anomaly Detection for Streaming Data
    Subutai Ahmad, Alexander Lavin, Scott Purdy, Zuha Agha
    machine learning, anomaly detection
    Published in Neurocomputing, June 20172017/06/02

    This paper, which appears in a special issue of Neurocomputing, demonstrates how Numenta's online sequence memory algorithm, Hierarchical Temporal Memory, meets the requirements necessary for real-time anomaly detection in streaming data. It also presents results using the Numenta Anomaly Benchmark (NAB), the first open-source benchmark designed for testing anomaly detection algorithms on streaming data.

  5. Continuous Online Sequence Learning with an Unsupervised Neural Network Model
    Yuwei Cui, Subutai Ahmad & Jeff Hawkins
    machine learning, sequence learning
    Published in Neural Computation, November 2016, Vol 28. No. 112016/11/01

    Analysis of HTM sequence memory applied to various sequence learning and prediction problems. Written with a machine learning perspective, the paper contains some comparisons to statistical and Deep Learning techniques.

  6. Page 1 of 3 Next >