IEEE Transactions on Automatic Control, Vol.46, No.3, 512-513, 2001
Author's Reply: Comments on "The unreasonable effectiveness of neural network approximation"
This note discusses issues raised in the comments on a recent paper. It explains why the original statement of the theorem in that paper is Correct as it stands, and clarifies the statements in the original paper. It points out how a proper understanding of the terminology resolves the first objection of the commentator and briefly outlines the directions the author is pursuing in a separate research based on the second and the third recommendations.