0.25
0.5
0.75
1.25
1.5
1.75
2
A note on the evaluation of generative models
Published on May 27, 20162741 Views
Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Given this wide range o
Related categories
Chapter list
A note on the evaluation of generative models00:00
Applications of generative models - 100:08
Applications of generative models - 202:01
Training generative models - 102:42
Training generative models - 202:57
Evaluating generative models 04:50
Sample plausibility - 104:55
Sample plausibility - 206:37
Parzen window estimates - 108:30
Parzen window estimates - 209:56
Log-likelihood10:42
Samples and log-likelihood12:31
Examples13:38
Samples and applications14:33
Conclusions15:30