I don't really understand it but I suspect there is some trick going on somewher... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Houshalter on July 27, 2015 \| parent \| context \| favorite \| on: Deep learning I don't really understand it but I suspect there is some trick going on somewhere. I don't see how you can avoid doing at least one computation for each weight pixel pair in each convolution.

varelse on July 27, 2015 [–]

Does this answer your question?

https://en.wikipedia.org/wiki/Convolution_theorem

Houshalter on July 29, 2015 | [–]

I read it, I just don't understand it.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact