Deep Learning WS 20/21

This video introduces visualization for architectures and monitoring training. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video explains sequence generation using RNNs. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses Gated Recurrent Units and compares them to Elman and LSTM Cells. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses Long-Short-Term Memory Units. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses the training of simple RNNs using the backpropagation through time algorithm. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video introduces the topic of recurrent neural networks and the Elman Cell. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses learning to learn options for architecture search and first results. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video demonstrates the many uses of residual connections in deep networks from Inception-ResNet to DenseNet. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses the ideas of residual connections in deep networks that allow going from 20 to more than 1000 layers. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science

This video discusses the success of deeper models including Inception V2 and V3. One key technology that is introduced in V3 is label smoothing regularization. Watch on:FAU TVFAU TV (no memes)YouTube Read the Transcript (Summer 2020) at:LMETowards Data Science