Sort by

Newest

Oldest

Popular

02.04 Multilayer Perceptrons
00:05:36
02.06 Activation Functions
00:10:19
12.07 Special Techniques for Optimizing Architectural Hyperparameters (NAS)
00:19:47
12.06 Speeding up HPO by Hyperparameter Gradient Descent
00:09:17
12.05 Speeding up HPO by Exploiting User Beliefs
00:15:43
12.04 Speedup Techniques for Blackbox HPO
00:23:46
12.03 Blackbox Optimization Methods for HPO
00:19:40
12.02 Manual HPO in Deep Learning
00:14:39
12.01 HPO in Deep Learning
00:08:40
11.06 Alternative Treatments of Uncertainty in Neural Networks
00:19:37
11.04 Markov Chain Monte Carlo (MCMC)
00:25:21
11.05 Prior Fitted Networks (PFNs)
00:27:12
11.03 Variational Inference
00:15:07
11.02 Being Bayesian about Neural Networks
00:09:46
11.01 Why we Need Uncertainty in Neural Networks
00:08:07
10.05 Diffusion Models
00:25:16
10.04 Generative Adversarial Networks (GANs)
00:18:55
10.03 Generative Models and the Variational Autoencoder (VAE)
00:38:03
10.02 Sparse and Denoising Autoencoders
00:16:40
10.01 Introduction to Autoencoders
00:13:53
09.06 Detection and Segmentation
00:22:15
09.05 CNN Architectures
00:24:27
09.04 Parameter Initialization
00:11:28
09.03 General Methodology
00:11:00
09.02 Transfer Learning
00:42:34
09.01 Normalization Layers
00:10:44
06.05 Miscellaneous Convolutions
00:27:20
08.07 Transformers: Putting it All Together
00:09:42
08.06 Transformer Encoder and Decoder Architecture
00:13:30
08.05 Self-Attention
00:25:42