# Conditional locality sensitive hashing associative memory

**URL:** <https://discourse.numenta.org/t/conditional-locality-sensitive-hashing-associative-memory/11361>\
**Category:** Lounge\
**Created:** [May 16, 2024, 12:54am UTC](https://discourse.numenta.org/t/conditional-locality-sensitive-hashing-associative-memory/11361 "2024-05-16T00:54:38Z")\
**Posts on this page:** 2\
**Page:** 1

<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:** [May 16, 2024, 12:54am UTC](https://discourse.numenta.org/t/conditional-locality-sensitive-hashing-associative-memory/11361/1 "2024-05-16T00:54:38Z")

</div>

I wrote this note about an idea I had:

[https://archive.org/details/conditional-lsh-am](https://archive.org/details/conditional-lsh-am)

After reading this Memory Mosaics paper on Arxiv where they replace neural networks in transformers with associative memory:

[https://arxiv.org/pdf/2405.06394](https://arxiv.org/pdf/2405.06394)

---

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [May 16, 2024, 9:34am UTC](https://discourse.numenta.org/t/conditional-locality-sensitive-hashing-associative-memory/11361/2 "2024-05-16T09:34:10Z")

</div>

Thanks for the paper reference, it is quite interesting.

Regarding your note on using a hyperplane to split data points in two equal sized subsets, I ran a small experiment with a slightly different purpose - to chose P out of N routes (or “clusters”) for e.g. a MoE with P=4/N=32 classifiers.

The problem there (as in your case) is to have a means for each plane to cut evenly (whatever the desired ratio is 1/2, 1/8 etc) through the data space.  
The algorithm can start with planes not entirely random but passing through the centroid of a sufficiently large number of points then shifting them “up” or “down” iteratively until you get a desired split ratio.