Completed
deep representations
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Learning with Symmetry and Invariance for Speech Perception
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 vision and speech
- 3 acoustic variability (words)
- 4 acoustic variability (sentences)
- 5 feedforward models for vision
- 6 invariance in auditory cortex and models
- 7 representations for recognition
- 8 bootstrapping for learning by children
- 9 statistical learning
- 10 data representation
- 11 deep representations
- 12 learning representations
- 13 invariant and selective representations
- 14 groups and visual transformations
- 15 orbit of group transformations
- 16 orbit are unique and invariant
- 17 invariance via group averaging
- 18 transferability
- 19 (probabilistic) selectivity
- 20 tl;dr summary
- 21 algorithms for signatures
- 22 computations for signatures
- 23 learning templates and transformations
- 24 learning by implicit supervision
- 25 Word orbits by signal manipulation
- 26 word representations
- 27 isolated word classification
- 28 how many templates and pooling functions?
- 29 MFCC comparison (linear kernel)
- 30 MFCC comparison (same dimensionality)
- 31 MFCC comparison (RBF kernel)
- 32 representation visualization
- 33 (segmental) phone representations
- 34 Sample complexity: vowel classification
- 35 multilayer frame representations
- 36 frame-based phone classification
- 37 learnable templates in CNNS
- 38 VTL-convolutional networks
- 39 acoustic modeling: HMM state classification
- 40 data augmentation?
- 41 looking forward
