On the ability of neural nets to express distributions — HN submission

Sat, 06 Apr 2024 17:13:14 GMT

Algebraic Simplification Neural Nets

It seems that there should be a way to algebraically simplify neural nets. Trivially a node that has a zero weight can be removed as can any links to / from that node. It should also be possible to eliminate nodes that have a full-value (aka '1' on the 0-1 scale) I have also seen work where the matrix multiplies during training can have columns "collapsed". The ultimate question might be applying an "algebraic simplification" of the final network to simplify a post-trained network used for inference. The idea is to take a path through a network, constructing the equation for that path…

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

On the ability of neural nets to express distributions · HackerPapers discussions

On the ability of neural nets to express distributions — HN submission