Generative Models I thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Generative Models I

Published on Jul 27, 201714322 Views

Related categories

Chapter list

Generative models I00:00
Density Estimation00:11
Sample Generation00:47
Maximum Likelihood01:30
Taxonomy of Generative Models - 103:01
Taxonomy of Generative Models - 203:21
Taxonomy of Generative Models - 304:32
Fully Visible Belief Nets - 104:42
Fully Visible Belief Nets - 205:46
Notable FVBNs06:54
Change of Variables07:43
Taxonomy of Generative Models - 409:33
Taxonomy of Generative Models - 510:02
Variational Learning10:33
Variational Bound12:19
Variational Autoencoder 13:38
For more information…14:40
Taxonomy of Generative Models - 614:58
Deep Boltzmann Machines15:35
Taxonomy of Generative Models - 716:25
Generative Stochastic Networks17:11
Taxonomy of Generative Models - 817:51
Generative Adversarial Networks17:59
Combining VAEs and GANs: Adversarial Variational Bayes20:05
What can you do with generative models? - 121:53
What can you do with generative models? - 222:48
Generative models for simulated training data23:43
What can you do with generative models? - 324:27
What is in this image?25:26
Generative modeling reveals a face25:55
What can you do with generative models? - 426:05
Supervised Discriminator26:23
Semi-Supervised Classification - 127:37
Semi-Supervised Classification - 228:13
What can you do with generative models? - 528:45
Next Video Frame Prediction - 129:44
Next Video Frame Prediction - 230:20
What can you do with generative models? - 631:07
iGAN31:39
Introspective Adversarial Networks33:14
Image to Image Translation33:29
Unsupervised Image-to-Image Translation36:34
CycleGAN38:27
Text-to-Image Synthesis40:38
What can you do with generative models? - 741:13
Simulating particle physics41:27
What can you do with GANs?43:15
Vector Space Arithmetic 43:22
Learning interpretable latent codes / controlling the generation process44:33
Plug and Play Generative Networks44:53
Basic idea 47:11
GAN loss is a key ingredient47:18
PPGN Samples48:42
Sampling without class gradient48:57
PPGN for caption to image49:17
For more information…49:35