This video discusses the first early architectures developed in deep learning from LeNet to GooLeNet.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses how to evaluate deep learning approaches.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses the problem of class imbalance and how to compensate for it.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses the use of validation data and how to choose architectures and hyperparameters and discuss ensembling.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses the use of validation data and how to choose optimizers, monitor weights, and set learning rates including their annealing.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses initialization techniques and transfer learning.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses normalization such as batch normalization and self normalizing units and explains the concepts of drop-out and drop-connect
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETowards Data Science
This video discusses classical regularization techniques such as early stopping using a validation set, augmentation, and maximum a-posteriori methods that expand the loss function using a regularization term.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at:LMETow...
This video discusses the problem of over- and underfitting. In order to get a better understanding, we explore the bias-variance trade-off and look into the effects of training data size and the number of parameters.
Watch on:FAU TVFAU TV (no memes)YouTube
Read the Transcript (Summer 2020) at...