Computational Intelligence and Neuroscience / 2021 / Article / Tab 1

Research Article

A Fast Spatial Pool Learning Algorithm of Hierarchical Temporal Memory Based on Minicolumn’s Self-Nomination

Table 1

The flow of SPL_SN.

(1) Encode the input
(2) Calculate the overlapping value between the minicolumn and the input
(3) Calculate the minicolumn’s self-nomination status according to the overlapping value
(4) Activate the minicolumns based on their self-nomination statuses and load-carrying capacity
(5) Update the loading capacity and adjust synapses on activated minicolumns