Revision as of 10:40, 4 September 2020 edit 2001:16b8:403a:3900:10ac:5987:da21:4c5 (talk) No edit summary ← Previous edit		Revision as of 10:41, 4 September 2020 edit undo 2001:16b8:403a:3900:10ac:5987:da21:4c5 (talk) No edit summary Next edit →
Line 69: === Arbitrary Width Case === I am wondering if the theorem presented here is correct. In http://www2.math.technion.ac.il/~pinkus/papers/acta.pdf, the neural network has only one node in output layer (so they map to R). Here the numer of output nodes is arbitrary. Is this correct?

Talk:Universal approximation theorem: Difference between revisions