User talk:2605:A601:AB0D:1800:4C1F:921E:AC57:344A

1. The criticizer is confusing lack of empirical evidence (i.e. the lack of software code associated with the Supersymmetric Artificial Neural Network?) with supposed lack of scientific evidence overall. The Supersymmetric Artificial Neural Network Paper referenced at [4], on the page, already mentions that there is no empirical evidence regarding the existence of software code for the Supersymmetric Artificial Neural Network, in the very abstract of said paper. Despite this, many machine learning papers are theoretical/hypothetical in nature.
 * Notably, despite the lack of existence of software code for Supersymmetric Artificial Neural Networks, notice that complicated gauge groups related to Supersymmetry, are similar to simpler gauge groups that empirically perform well in machine learning, as cited throughout the page.

2. Contrary to claims of the criticizer, that there are supposedly no equations, there are mathematical equations especially in this section of the page.

3. The page also includes novel mathematical notations introduced by Jordan Bennett, as seen for example in Notation 2 (in addition to several other mathematical notations used to construct the argument):


 * Novel Notation Introduced By Jordan - Notation 2 - Supermanifold Learning: $$ \phi \big(x; \theta, \bar \big)^{\top}w $$

The novel notation above, while concerning supermanifolds/supersymmetry, builds atop prior Deep Learning notation, seen in Notation 1 - Manifold Learning: $$ \phi \big(x; \theta \big)^{\top}w $$, which does not concern supermanifolds/supersymmetry, but manifolds instead.

Recommended reading to the Criticizer at the courtesy of the author, Jordan Bennett
1. My “Supersymmetric Artificial Neural Network” in layman’s terms

2. A review of the Supersymmetric Artificial Neural Network" by Mitchell Porter