Lecture
Statistical Interpretation of Artificial Neural Networks
Description
This lecture focuses on the statistical interpretation of artificial neural networks, deriving the cross-entropy error function in the context of the likelihood of data under a neural network model. It covers the generation of predicted labels, the likelihood of input-output pairs, and the maximum likelihood for neural networks by minimizing the negative log-likelihood.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.