Praphul Chandra, Y. Narahari, et al.
AAAI/IAAI 2015
In the Hierarchical Temporal Memory (HTM) paradigm the effect of overlap between inputs on the activation of columns in the spatial pooler is studied. Numerical results suggest that similar inputs are represented by similar sets of columns and dissimilar inputs are represented by dissimilar sets of columns. It is shown that the spatial pooler produces these results under certain conditions for the connectivity and proximal thresholds at initialization. Qualitative arguments about the learning dynamics of the spatial pooler are then discussed.
Praphul Chandra, Y. Narahari, et al.
AAAI/IAAI 2015
Anika Schumann, Freddy Lecue
AAAI/IAAI 2015
Kareem Amin, Satyen Kale, et al.
AAAI/IAAI 2015
Wei Liu, Cun Mu, et al.
AAAI/IAAI 2015