Co-occurring keywords
Papers
A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning
CVPR 2017
Efficient Knowledge Distillation from an Ensemble of Teachers
INTERSPEECH 2017
Generalized Distillation Framework for Speaker Normalization
INTERSPEECH 2017
Student-Teacher Training with Diverse Decision Tree Ensembles
INTERSPEECH 2017
How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval
IJCAI 2017
Transfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages
INTERSPEECH 2017
Network Morphism
ICML 2016
Sequence Student-Teacher Training of Deep Neural Networks
INTERSPEECH 2016
Model Compression Applied to Small-Footprint Keyword Spotting
INTERSPEECH 2016
Dropout distillation
ICML 2016
Robust Speech Recognition Using Generalized Distillation Framework
INTERSPEECH 2016
Bayesian dark knowledge
NIPS 2015
Do Deep Nets Really Need to be Deep?
NIPS 2014