Talk:Convolutional neural network

Introduction

"only 25 neurons are required to process 5x5-sized tiles". Shouldn't that be "weights" and not "neurons"? Earlier it said "10,000 weights would be required for processing an image sized 100 × 100 pixels". Ulatekh (talk) 15:53, 19 March 2024 (UTC)

Absolutely, you're right. I was going to ask the same question. 25 weights for each neuron in the second layer from each neuron in the input layer, and all these 25 weights don't vary as the filter is slid across the input. Do you want to make the correction or should I, since the original editor is not responding? Iuvalclejan (talk) 22:47, 25 January 2025 (UTC)

I made the change. 2600:6C5D:577F:F44E:B9B2:E830:3647:8315 (talk) 14:20, 27 January 2025 (UTC)

Wiki Education assignment: Linguistics in the Digital Age

This article was the subject of a Wiki Education Foundation–supported course assignment, between 15 January 2025 and 9 May 2025. Further details are available on the course page. Student editor(s): AshlaMaOmao (article contribs).

— Assignment last updated by FblthpTheLost (talk) 00:10, 8 May 2025 (UTC)

Should deconvolution use matrix inverses rather than transposes?

If you are doing true de-convolution, you need to multiply by the inverse of the convolution operator. Only in special cases is that the same as the transpose. Unless the argument that this isn't real convolution makes a difference, I assume that the same applies here. If it really is a special case, that needs highlighting. Actually, in real convolution, there is no true inverse, as information is lost.

-- David Woolley (talk) 13:50, 9 July 2026 (UTC)