Encoding Reality: Prediction-Assisted Cortical Learning Algorithm in Hierarchical Temporal Memory
This work advances the Hierarchical Temporal Memory model, a neuroscience-inspired approach to machine learning, by refining its core algorithm for improved performance and biological plausibility.
The paper presents a rigorous mathematical formulation of the Cortical Learning Algorithm (HTM) and introduces Prediction Assisted CLA (paCLA), which enhances computational power and aligns more closely with neuroscience principles.
In the decade since Jeff Hawkins proposed Hierarchical Temporal Memory (HTM) as a model of neocortical computation, the theory and the algorithms have evolved dramatically. This paper presents a detailed description of HTM's Cortical Learning Algorithm (CLA), including for the first time a rigorous mathematical formulation of all aspects of the computations. Prediction Assisted CLA (paCLA), a refinement of the CLA is presented, which is both closer to the neuroscience and adds significantly to the computational power. Finally, we summarise the key functions of neocortex which are expressed in paCLA implementations.