0.25
0.5
0.75
1.25
1.5
1.75
2
Classification with Deep Invariant Scattering Networks
Published on 2013-01-1616438 Views
High-dimensional data representation is in a confused infancy compared to statistical decision theory. How to optimize kernels or so called feature vectors? Should they increase or reduce dimension
Related categories
Presentation
Classification with Deep Invariant Networks00:00
High Dimensional Classification - 100:24
High Dimensional Classification - 201:44
Deep Neural Networks - 104:06
Deep Neural Networks - 206:09
Intra-Class Variability08:37
Translations and Deformations10:58
Rotation and Scaling Variability11:53
Frequency Transpositions - 112:23
Frequency Transpositions - 213:00
Frequency Transpositions - 313:06
Cascade of Transformation Groups13:16
Understanding Deep Networks14:46
Stable Discriminant Invariants - 116:04
Stable Discriminant Invariants - 216:05
Stable Discriminant Invariants - 316:34
Stable Discriminant Invariants - 416:42
Stable Discriminant Invariants - 517:11
Stable Discriminant Invariants - 617:23
Stable Discriminant Invariants - 717:30
Stable Discriminant Invariants - 817:41
Stable Discriminant Invariants - 917:49
Stable Discriminant Invariants - 1017:51
Stable Discriminant Invariants - 1117:55
Stable Discriminant Invariants - 1218:00
Stable Discriminant Invariants - 1318:01
Stable Discriminant Invariants - 1418:02
Stable Translation Invariants - 118:09
Stable Translation Invariants - 218:10
Stable Translation Invariants - 318:25
Stable Translation Invariants - 418:31
Stable Translation Invariants - 518:38
Stable Translation Invariants - 618:42
Stable Translation Invariants - 718:58
Stable Translation Invariants - 819:14
Wavelet Transform - 119:31
Wavelet Transform - 220:11
Why Wavelets ?20:38
Image Wavelet Transform21:07
Wavelet Translation Invariance - 121:38
Wavelet Translation Invariance - 221:58
Wavelet Translation Invariance - 322:15
Recovering Lost Information23:02
Deep Convolution Network - 123:56
Deep Convolution Network - 224:01
Deep Convolution Network - 324:10
Deep Convolution Network - 424:19
Scattering Vector - 124:37
Scattering Vector - 224:44
Amplitude Modulation - 124:52
Amplitude Modulation - 225:05
Amplitude Modulation - 325:26
Textures with Same Spectrum - 125:49
Textures with Same Spectrum - 226:06
Textures with Same Spectrum - 326:17
Scattering Cascade - 126:32
Scattering Cascade - 226:49
Scattering Cascade - 327:05
Scattering Properties27:37
Scattering Inversion: Phase Recovery - 128:24
Scattering Inversion: Phase Recovery - 228:26
Scattering Inversion: Phase Recovery - 328:56
Scattering Inversion: Phase Recovery - 429:05
Audio Reconstruction - 129:19
Audio Reconstruction - 229:31
Audio Reconstruction - 329:48
Digit Classification: MNIST30:05
Classification of Textures31:24
How to Cascade Invariants?32:17
Roto-Translation Group - 133:06
Roto-Translation Group - 233:27
Roto-Translation Group - 333:46
Roto-Translation Group - 433:55
Roto-Translation Group - 534:05
Wavelet Transform on a Group - 134:17
Wavelet Transform on a Group - 234:46
Wavelet Transform on a Group - 335:00
Wavelet Transform on a Group - 435:28
Wavelet Transform on a Group - 535:52
Rotation and Scaling Invariance36:18
Learning: Group Pursuit36:50
Stable Parts and Wavelets - 138:09
Stable Parts and Wavelets - 239:00
Stable Parts and Wavelets - 339:39
Sparse Learning of Stable Parts - 139:50
Sparse Learning of Stable Parts - 240:41
Sparse Learning of Stable Parts - 341:01
Conclusion41:39