It doesn’t surprise me. It’s been known a long time that you can model arbitrary... | Hacker News

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

		PaulHoule on June 22, 2023 \| parent \| context \| favorite \| on: Any Deep ReLU Network Is Shallow It doesn’t surprise me. It’s been known a long time that you can model arbitrary functions with a 3-layer network with logistic activation.

RobbieGM on June 22, 2023 [–]

Do you have any further information or a source for this? As someone unfamiliar with ML, this sounds crazy to me.

hazrmard on June 22, 2023 | [–]

It was first proposed here[1]: "Approximation by superpositions of a sigmoidal function"

[1]: https://link.springer.com/content/pdf/10.1007/BF02551274.pdf

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