From 8a855bd16d1c0a7e22a53ae57892cbbf630134ee Mon Sep 17 00:00:00 2001 From: Nando Farchmin <nando.farchmin@gmail.com> Date: Fri, 1 Jul 2022 19:26:17 +0200 Subject: [PATCH] Fix typo --- doc/basics.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/doc/basics.md b/doc/basics.md index a9ec093..1b7bdbe 100644 --- a/doc/basics.md +++ b/doc/basics.md @@ -128,6 +128,12 @@ The empirical regression problem then reads > **Definition** (loss function): > A _loss functions_ is any function, which measures how good a neural network approximates the target values. +Typical loss functions for regression and classification tasks are + - mean-square error (MSE, standard $`L^2`$-error) + - weighted $`L^p`$- or $`H^k`$-norms (solutions of PDEs) + - cross-entropy (difference between distributions) + - Kullback-Leibler divergence, Hellinger distance, Wasserstein metrics + - Hinge loss (SVM) To find a minimizer of our loss function $`\mathcal{L}_N`$, we want to use the first-order optimality criterion -- GitLab