Lecture Videos

This video presents a variety of modern activation functions including the quest for finding new ones. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we start introducing discriminant transforms and look at their basic concept. Watch on:FAU TVYouTube

This video presents the biological background of activation functions and the classical choices that were used for neural networks. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we have a look at the naive Bayes classifier. Watch on:FAU TVYouTube

This video discusses details on optimization and different options in gradient descent procedure such as momentum and ADAM. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we learn how to estimate the parameters of the logistic function effectively. Watch on:FAU TVYouTube

This video explains hinge loss and its relation to support vector machines. We also show why sub-gradients allow us to optimize factions that are not continuously differentiable. Furthermore, the hinge loss enables to embed optimization constraints into loss functions. Watch on:FAU TVFAU TV (no ...

This video explains how to derive L2 Loss and Cross-Entropy Loss from statistical assumptions. Highly relevant for the exam! Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we look into the actual logistic regression and how to formulate the optimization problem. Watch on:FAU TVYouTube

This video explains backpropagation at the level of layer abstraction. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science