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.
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.
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.
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.
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.