Perceptual hashes for large SDR machines

[maxerbubba]

Regarding perceptual hash, there’s some interesting work that uses a hash + pooling to output an SDR:

“ A neural algorithm for a fundamental computing problem”

Memory representation in moth olfactory network, role of neuromodulators

This paper expands on that and provides some more computational/mathematical interpretation: Sanjoy Dasgupta, Charles F. Stevens, Saket Navlakha – A neural algorithm for a fundamental computing problem key take aways fly olfactory brain is an implementation of the HTM spatial pooler (my interpretation) mathematically it’s an implementation of dimensionality reduction by random projections, relying on locality guarantees provided by the Johnson-Lindenstrauss lemma that I mentioned bef…

And later

BioHash: biologically-inspired hashing into "sparse expansive representations"

Are “Sparse expansive representations” the same as SDRs? It is interesting that the authors of this paper found a common solution, but from a different domain (fruit fly olfactory circuits). Bio-Inspired Hashing for Unsupervised Similarity Search https://arxiv.org/pdf/2001.04907.pdf BioHash is based on another paper (with Hopfield and Krotov) that introduced “FlyHash”. BioHash uses a biologically-plausible learning rule, while FlyHash does not do any learning on the dataset. Personally, I…