Author: Andreas Maier

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

In this video, we look into further probability density and mass functions of the exponential family. Watch on:FAU TVYouTube

This video introduces the basics of the backpropagation algorithm. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we combine the logistic function with the Gaussian probability density function. Watch on:FAU TVYouTube

This video introduces the topics of activation functions, loss, and the idea of gradient descent. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

In this video, we introduce the logistic function. Watch on:FAU TVYouTube

This video introduces the topic of feedforward networks, universal approximation, and how to map a decision tree onto a neural network. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science