Intro to Deep Learning and Generative Models Course - L8.2 Logistic Regression Loss Function

Sebastian's books: https://sebastianraschka.com/books/ In the previous video, we saw that we can view logistic regression as a single-layer neural networks. We also discussed how the forward pass works for making predictions. However, logistic regression comes with a set of weights we have to optimize in order to make "good" (that is, correct) predictions. In this video, we will learn about the logistic regression loss function. The optimization procedure will then be the same as for Adaline. In Adaline, we differentiated the mean squared error loss with respect to the weights in order to learn the weights. In logistic regression, we differentiate the logistic loss instead of the mean squared error loss. Slides: https://sebastianraschka.com/pdf/lecture-notes/stat453ss21/L08_logistic__slides.pdf ------- This video is part of my Introduction of Deep Learning course. Next video: https://youtu.be/7rR1L7t2EnA The complete playlist: https://www.youtube.com/playlist?list=PLTKMiZHVd_2KJtIXOW0zFhFfBaJJilH51 A handy overview page with links to the materials: https://sebastianraschka.com/blog/2021/dl-course.html ------- If you want to be notified about future videos, please consider subscribing to my channel: https://youtube.com/c/SebastianRaschka