Jeff Hawkins and Subutai Ahmad

Neuroscience, Sequence Learning

Published in Frontiers in Neural Circuits Journal (Peer-reviewed) • 2016/03/30

Neuroscience, Sequence Learning

Published in Frontiers in Neural Circuits Journal (Peer-reviewed) • 2016/03/30

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.

Yuwei Cui, Subutai Ahmad and Jeff Hawkins

Neuroscience, Sparse Distributed Representations

Published in Frontiers in Neuroscience (Peer-reviewed) • 2017/11/29

Neuroscience, Sparse Distributed Representations

Published in Frontiers in Neuroscience (Peer-reviewed) • 2017/11/29

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 the HTM spatial pooler.

Subutai Ahmad, Alexander Lavin, Scott Purdy and Zuha Agha

Anomaly Detection, Machine Learning

Published in Neurocomputing (Peer-reviewed) • 2017/06/02

Anomaly Detection, Machine Learning

Published in Neurocomputing (Peer-reviewed) • 2017/06/02

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.

Yuwei Cui, Subutai Ahmad and Jeff Hawkins

Machine Learning, Sequence Learning

Published in Neural Computation (Peer-reviewed) • 2016/11/01

Machine Learning, Sequence Learning

Published in Neural Computation (Peer-reviewed) • 2016/11/01

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.

Mirko Klukas, Marcus Lewis and Ila Fiete

Grid Cells, Neuroscience

Preprint of journal submission • 2019/03/16

Grid Cells, Neuroscience

Preprint of journal submission • 2019/03/16

This paper shows that a set of grid cell modules, each with only 2D responses, can generate unambiguous and high-capacity representations of variables in much higher-dimensional spaces.