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.
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).
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.
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.
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.