In plain words: Instead of wiring the brain-inspired pattern detector with random connections, this design sets its links from the input data, keeping the data's natural sparsity, and builds it as a chip mixing memory resistors with standard circuits. On face recognition it beat the usual random version.
Abstract · Feature extraction without learning in an analog Spatial Pooler memristive-CMOS circuit design of Hierarchical Temporal Memory
Hierarchical Temporal Memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.
Olga Krestinskaya, Alex Pappachen James
arXiv:1803.05131 · cs.ET, cs.AI, cs.AR, cs.NE · submitted Mar 14, 2018
abstract · pdf · html
Hierarchical Temporal Memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This sparsity is introduced by the binary weights and random weight assignment in the initialization stage of the HTM. We propose the alternative deterministic method for the HTM initialization stage, which connects the HTM weights to the input data and preserves natural sparsity of the input information. Further, we introduce the hardware implementation of the deterministic approach and compare it to the traditional HTM and existing hardware implementation. We test the proposed approach on the face recognition problem and show that it outperforms the conventional HTM approach.