Encoding Data for HTM Systems — mentioned by 19h

Fri, 04 Nov 2022 03:30:52 GMT

We've been doing significant research using HTM[1][2][3][4] w/ SDR[5] similar to the proprietary implementation of Semantic Folding[6] and were able to classify literally gigabytes of documents per second on FPGAs. HTM aims to resemble the architecture of the Neocortex. I simply don't understand why literally everyone immediately jumps at CNNs, RNNs (transformers et al.) -- they're extremely expensive, slow and definitely not usable for SIGINT-sized intel projects. [1] https://arxiv.org/pdf/2112.14820.pdf [2] https://arxiv.org/pdf/1402.2902.pdf [3] https://arxiv.org/pdf/1509.08255.pdf [4]…

Paper and discussion history. A mention is not an endorsement.

Encoding Data for HTM Systems · HackerPapers discussions

Encoding Data for HTM Systems — mentioned by 19h