Numenta Logo
Research Publications

Outside Research

  1. Structural Plasticity on the SpiNNaker Many-Core Neuromorphic System
    Petruț A. Bogdan*, Andrew G. D. Rowley, Oliver Rhodes and Steve B. Furber
    Hardware implementations of HTM
    Published in Frontiers in Neuroscience2018/07/02

    Structural plasticity is required by HTM models, but not addressed in many hardware architectures. This paper presents a model of topographic map formation that is implemented on the SpiNNaker neuromorphic platform, running in real time using point neurons, and making use of both synaptic rewiring and spike-timing dependent plasticity (STDP). The authors use our papers as one of the motivations for working on this architecture.

  2. Detecting performance anomalies in scientific workflows using hierarchical temporal memory
    Maria A.Rodriguez, Ramamohanarao Kotagiri, Rajkumar Buyya
    Anomaly Detection
    Published in Future Generation Computer Systems2018/05/18

    This paper proposes an anomaly detection framework for scientific workflows that is based on our Hierarchical Temporal Memory (HTM) technology. The paper also cites the Numenta Anomaly Benchmark (NAB) scoring code and methodology; the researchers use NAB to evaluate performance of algorithms.

  3. A Distributed Anomaly Detection System for In-Vehicle Network Using HTM Anomaly Detection papers
    Chundong Wang, Zhentang Zhao, Liangyi Gong, Likun Zhu, Zheli Liu, Xiaochun Cheng
    Anomaly Detection
    IEEE Access2018/01/30

    The authors proposes a distributed anomaly detection system using hierarchical temporal memory (HTM) that predicts the flow of data in real time to increase security for a vehicular controller area network bus. The HTM-based anomaly detection system achieved better results than systems based on recurrent neural networks and hidden Markov model detection.

  4. Predictive Coding of Novel versus Familiar Stimuli in the Primary Visual Cortex
    Jan Homann, Sue Ann Koay, Alistair M. Glidden, David W. Tank, Michael J. Berry II
    Sequence Learning
    Pre-print of journal submission 2017/10/03

    The experimental paper explores theories of predictive coding by presenting mice with repeated sequences of images where novel images are occasionally substituted. Many of the findings have strong relationships to the characteristics of HTM Sequence Memory. The discussion section of this paper explores this relationship and includes a paragraph on one of our papers, “Why Neurons Have Thousands of Synapses, a Theory of Sequence Memory in Neocortex.”

  5. Hierarchical Temporal Memory Based Autonomous Agent for Partially Observable Video Game Environments
    Al’i Kaan Sungur
    Sequence Learning
    Thesis: The Graduate School of Informatics Institute of Middle East Technical University2017/08/01

    This Master’s thesis explores the feasibility of a Hierarchical Temporal Memory (HTM) based game agent that can explore its environment and learn rewarding behaviors. The unsupervised agent learns action sequences with respect to a stimulated reward in real time, navigating a procedurally generated 3D environment and modeling the patterns that stream to its visual sensor.

  6. Page 1 of 3 Next >