Research Papers
The HTM Spatial Pooler—A Neocortical Algorithm for Online Sparse Distributed Coding
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 the HTM spatial pooler.
AUTHORS:
Yuwei Cui, Subutai Ahmad and Jeff Hawkins
PUBLICATION:
Published in Frontiers in Neuroscience (Peer-reviewed)
A Theory of How Columns in the Neocortex Enable Learning the Structure of the World
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.
AUTHORS:
Jeff Hawkins, Subutai Ahmad and Yuwei Cui
PUBLICATION:
Published in Frontiers in Neural Circuits Journal (Peer-reviewed)
Untangling Sequences: Behavior vs. External Causes
This paper describes a cortical model for untangling sensorimotor from external sequences. It shows how a single neural mechanism can learn and recognize these two types of sequences: sequences where sensory inputs change due to external factors, and sequences where inputs change due to our own behavior (sensorimotor sequences).
AUTHORS:
Subutai Ahmad and Jeff Hawkins
PUBLICATION:
Preprint of journal submission
Unsupervised Real-Time Anomaly Detection for Streaming Data
This paper demonstrates how Numenta’s online sequence memory algorithm, HTM, meets the requirements necessary for real-time anomaly detection in streaming data. It presents results using the Numenta Anomaly Benchmark (NAB), the first open-source benchmark designed for testing real-time anomaly detection algorithms.
AUTHORS:
Subutai Ahmad, Alexander Lavin, Scott Purdy and Zuha Agha
PUBLICATION:
Published in Neurocomputing (Peer-reviewed)
Continuous Online Sequence Learning with an Unsupervised Neural Network Model
This paper contains an 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.
AUTHORS:
Yuwei Cui, Subutai Ahmad and Jeff Hawkins
PUBLICATION:
Published in Neural Computation (Peer-reviewed)
Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex
This foundational paper describes core HTM theory for sequence memory and its relationship to the neocortex. Written with a neuroscience perspective, the paper explains why neurons have so many synapses and how networks of neurons can form a powerful sequence learning mechanism.
AUTHORS:
Jeff Hawkins and Subutai Ahmad
PUBLICATION:
Published in Frontiers in Neural Circuits Journal (Peer-reviewed)