9b10a919ddeb07e103dc05ff523afe38-AuthorFeedback.pdf

This statement is not a guarantee of global optimum for LHS (i.e,I(ˆX;X)), but rather a justifica-30 tion of why maximizing LHS can lead to desirable redundancies in RHS (i.e.I(X;X|Z) = 0). By using neural31 network, we have experimentally shown (for genetic and MNIST) that it is sufficiently flexible to achieve highly32 accurate results.