Deep Learning WS 20/21

Watch now: Deep Learning: Deep Learning: Activations, Convolutions, and Pooling – Part 4 (WS 20/21) (WS 20/21)

This video presents max and average pooling, introduces the concept of fully convolutional networks, and hints on how this is used to build deep networks. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

November 23, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 3 (WS 20/21)

This video presents convolutional layers including the concepts of strided and dilated convolutions and how to compute their gradient. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

November 20, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 2 (WS 20/21)

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

November 19, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 1 (WS 20/21)

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

November 18, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Loss and Optimization – Part 3 (WS 20/21)

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

November 17, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Loss and Optimization – Part 2 (WS 20/21)

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 ...

November 16, 2020 Kategorie: Deep Learning WS 20/21

Watch now: Deep Learning: Deep Learning: Activations, Convolutions, and Pooling – Part 4 (WS 20/21) (WS 20/21)

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 3 (WS 20/21)

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 2 (WS 20/21)

Watch now: Deep Learning: Activations, Convolutions, and Pooling – Part 1 (WS 20/21)

Watch now: Deep Learning: Loss and Optimization – Part 3 (WS 20/21)

Watch now: Deep Learning: Loss and Optimization – Part 2 (WS 20/21)

Watch now: Deep Learning: Loss and Optimization – Part 1 (WS 20/21)

Watch now: Deep Learning: Feedforward Networks – Part 4 (WS 20/21)

Watch now: Deep Learning: Feedforward Networks – Part 3 (WS 20/21)

Watch now: Deep Learning: Feedforward Networks — Part 2 (WS 20/21)