More neurons in the hidden layer than predictive features in neural nets
Year: 2024
Type: other
Abstract: This week, we were talking about neural networks for the first time, and I was saying that, in many illustrations of neural networks, there was a layer with fewer neurons than predictive variables, but sometimes, it could make sense to have more neurons in the layer than predictive variables, To illustrate, consider a simple example with one single variable [latex]x[/latex], and a binary outcome [latex]y\in\{0,1\}[/latex] set.seed(12345) n = 100 x = c(runif(n),1+runif(n),2+runif(n)) y = rep(...
Source: OpenEdition (OpenEdition)
DOI: 10.58079/12ky8
Author: Arthur Charpentier
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6917867464
Cites:
Cited by:
Related to: