Lecture

Optimization in Machine Learning: Gradient Descent

Description

This lecture introduces optimization in machine learning, focusing on gradient descent. It covers the analytical solution for linear regression, the lack of analytical solutions for logistic regression, and the use of specialized optimizers. The concept of convexity, stochastic gradient descent, and early stopping are explained. Practical considerations such as choosing a good learning rate and preprocessing data are discussed. The lecture also delves into solving the XOR problem without feature engineering using logistic regression and neural networks.

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.