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

**URL:** <https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721>\
**Category:** Tangential Theories\
**Created:** [July 14, 2020, 1:36am UTC](https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721 "2020-07-14T01:36:53Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![maxerbubba](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/maxerbubba/32/4804_2.png) [@maxerbubba](https://discourse.numenta.org/u/maxerbubba)\
**Post date:** [July 14, 2020, 1:36am UTC](https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721/1 "2020-07-14T01:36:53Z")

</div>

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](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 am curious if Olfactory circuits benefitted from having a NeoCortex before Auditory or Visual sensors ever did… and if the mysterious algorithm for Visual scene understanding has a simpler implementation in the Olfactory system.

---

<div class="post-metadata">

**Author:** ![SeanOConnor](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/seanoconnor/32/3441_2.png) [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Post date:** [July 14, 2020, 6:26am UTC](https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721/2 "2020-07-14T06:26:18Z")

</div>

The fastest random projection/LSH you can do on a digital computer is HD where H is the Walsh Hadamard matrix (ie. use the transform) and D is a diagonal matrix with random +1,-1 entries. That is a fully connected random projection where a change in one input affects all the outputs. HDHD is better yet. Of course you can do faster not fully connected random projections.  
I think you could do fully connected biological random projections very quickly using very few layers of computation because 1 neuron can connect to thousands of others. 2 layers of randomly connected neurons should be able to do a 1 million dimension random projection.

---

<div class="post-metadata">

**Author:** ![momiji](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/momiji/32/3719_2.png) [@momiji](https://discourse.numenta.org/u/momiji)\
**Post date:** [July 26, 2020, 11:55am UTC](https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721/3 "2020-07-26T11:55:58Z")

</div>

> [@maxerbubba](#):
>
> Are “Sparse expansive representations” the same as SDRs?

This kind of gets my ‘goat’, as to me they seem fundamentally the same thing, bar a specific constraint of being expansive, (no reason to structure an SDR thus either). So why not cite the SDR work by numenta at the very least?

Seems a bit disingenuous to me, unless i’ve read this wrong.

---

<div class="post-metadata">

**Author:** ![maxerbubba](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/maxerbubba/32/4804_2.png) [@maxerbubba](https://discourse.numenta.org/u/maxerbubba)\
**Post date:** [July 26, 2020, 8:25pm UTC](https://discourse.numenta.org/t/biohash-biologically-inspired-hashing-into-sparse-expansive-representations/7721/4 "2020-07-26T20:25:07Z")

</div>

Looks like the BioHash paper wasn’t accepted in a conference last year, so maybe that’s karma 🧐