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

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="1"><hr/></td></tr><tr><td class="align_left">(1) Encode the input<br/>(2) Calculate the overlapping value between the minicolumn and the input<br/>(3) Calculate the minicolumn’s self-nomination status according to the overlapping value<br/>(4) Activate the minicolumns based on their self-nomination statuses and load-carrying capacity<br/>(5) Update the loading capacity and adjust synapses on activated minicolumns</td></tr><tr class="table-tr"><td colspan="1"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Computational Intelligence and Neuroscience

tab1

Table 1

Table 1: A Fast Spatial Pool Learning Algorithm of Hierarchical Temporal Memory Based on Minicolumn’s Self-Nomination 