[Article] Edward Witten/String theory powered artificial neural network (how to build)

Disclaimer: I don’t know for sure, although I have a rough idea as discussed throughout this post.

But first off, why build an “Edward Witten/String theory powered artificial neural network”?

Image snippet 1 with math symbols, because medium doesn’t appear to support LAtex. (HQ version: https://i.imgur.com/R6i9AJc.png)

I call an “Edward Witten/String theory powered artificial neural network” or “Supersymmetric Artificial Neural Network”, ‘simply’ an artificial neural network that learns supersymmetric weights.

Looking at the above progression of ‘solution geometries’; going from SO(n) representation to SU(n) representation has guaranteed richer and richer representations in weight space of the artificial neural network, and hence better and better hypotheses were generatable. It is only then somewhat natural to look to SU(m|n) representation, i.e. the “Edward Witten/String theory powered artificial neural network” (“Supersymmetric Artificial Neural Network”).

To construct an “Edward Witten/String theory powered artificial neural network”, it may be feasible to start with a grassmann manifold artificial neural network then generate ‘charts’ until scenarios occur where the “Edward Witten/String theory powered artificial neural network” is achieved, in the following way:

Image snippet 2 with math symbols, because medium doesn’t appear to support LAtex. (HQ version: https://i.imgur.com/KBgI2ME.png)

Thought Curvature paper:

https://www.researchgate.net/Thought_Curvature

Github-page:

https://github.com/JordanMicahBennett/Supersymmetric-artificial-neural-network

Author:

http://folioverse.appspot.com