0.25
0.5
0.75
1.25
1.5
1.75
2
Deep Learning
Published on Sep 13, 201532925 Views
Related categories
Chapter list
Deep Learning00:00
Currect Student and Postdocs00:48
Mining for Structure - 101:09
Mining for Structure - 202:02
Deep Generative Model02:12
Multimodal Data03:16
Example: Understanding Images03:32
Caption Generation05:11
Talk Roadmap - 105:41
Learning Feature Representations - 106:28
Learning Feature Representations - 206:47
Traditional Approaches07:04
Computer Vision Features - 107:27
Computer Vision Features - 207:53
Audio Features - 108:09
Audio Features - 208:12
Restricted Boltzmann Machines08:18
Learning features08:54
Model Learning - 109:28
Model Learning - 210:45
RBMs for Real-valued Data - 111:25
RBMs for Real-valued Data - 211:59
RBMs for Real-valued Data - 312:14
RBMs for Word Counts - 112:37
RBMs for Word Counts - 213:40
Different Data Modalities14:24
Product of Experts - 116:13
Product of Experts - 218:27
Deep Boltzmann Machines - 119:34
Deep Boltzmann Machines - 219:48
Model Formulation20:27
Mathematical Formulation - 122:25
Mathematical Formulation - 222:48
Mathematical Formulation - 323:25
Approximate Learning - 124:29
Approximate Learning - 24:41
Approximate Learning - 326:17
Previous Work26:34
New Learning Algorithm - 127:36
New Learning Algorithm - 228:15
New Learning Algorithm - 330:34
Stochastic Approximation31:06
Learning Algorithm33:02
Variational Inference - 135:22
Variational Inference - 240:05
Variational Inference - 341:06
Variational Inference - 441:35
Good Generative Model? - 141:42
Good Generative Model? - 242:20
Good Generative Model? - 342:40
Good Generative Model? - 442:48
Good Generative Model? - 543:21
Good Generative Model? - 643:52
Handwriting Recognition44:38
Generative Model of 3-D Objects45:12
3-D Object Recognition45:55
Talk Roadmap - 246:41
Data - Collection of Modalities46:57
Shared Concept47:24
Multi-Modal Input47:34
Challenges - I48:04
Challenges - II - 148:44
Challenges - II - 249:06
A Simple Multimodal Model49:16
Multimodal DBM - 149:41
Multimodal DBM - 249:44
Multimodal DBM - 349:45
Multimodal DBM - 449:58
Multimodal DBM - 550:35
Text Generated from Images - 151:11
Text Generated from Images - 252:19
Images from Text53:00
MIR-Flickr Dataset53:21
Data and Architecture53:37
Results - 154:24
Results - 254:36
Generating Sentences54:55
Talk Roadmap - 356:45
Markov Random Fields57:29
Restricted Boltzmann Machines58:27
Model Selection59:19
Generative Model01:00:05
Model Selection - 101:01:02
Model Selection - 201:01:18
Simple Importance Sampling01:01:40
Annealing Between Distributions - 101:05:19
Annealing Between Distributions - 201:08:03
Annealed Importance Sampling Run01:08:37
AIS is Importance Sampling - 101:09:33
AIS is Importance Sampling - 201:14:24
RBMs with Geometric Averages01:14:39
Problems with Undirected Models01:15:16
Motivation: RBM Sampling - 101:17:31
Motivation: RBM Sampling - 201:17:35
Motivation: RBM Sampling - 301:17:40
Motivation: RBM Sampling - 401:17:41
Motivation: RBM Sampling - 501:17:42
Motivation: RBM Sampling - 601:17:42
Motivation: RBM Sampling - 701:17:51
Unrolled RBM as a Deep Generative Model - 101:18:07
Unrolled RBM as a Deep Generative Model - 201:18:10
Unrolled RBM as a Deep Generative Model - 301:18:10
Unrolled RBM as a Deep Generative Model - 401:18:11
Unrolled RBM as a Deep Generative Model - 501:18:11
Unrolled RBM as a Deep Generative Model - 601:18:20
Reverse AIS Estimator (RAISE) - 101:18:30
Reverse AIS Estimator (RAISE) - 201:19:03
Reverse AIS Estimator (RAISE) - 301:19:41
MNIST - 101:20:24
MNIST - 201:21:08
Omniglot Dataset01:21:23
MNIST and Omniglot Results01:21:39
DBMs and DBNs01:22:10
Helmholtz Machines01:22:39