wat? I've worked in neural nets for 30 years and I've never needed group theory. just linear algebra, multivariate calculus, number theory.
I appreciate that symmetries are great but that doesn't solve a problem.
I appreciate that symmetries are great but that doesn't solve a problem.
http://proceedings.mlr.press/v76/ensign17a/ensign17a.pdf
"The key idea behind our results is that if we can find the symmetries of a problem then we can solve it"