Open AccessPosted Content
Distilling the Knowledge in a Neural Network
Reads0
Chats0
TLDR
This work shows that it can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model and introduces a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.Abstract:
A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel.read more
Citations
More filters
Posted Content
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.
Zeyuan Allen-Zhu,Yuanzhi Li +1 more
TL;DR: It is proved that self-distillation can also be viewed as implicitly combining ensemble and knowledge distillation to improve test accuracy, and it sheds light on how ensemble works in deep learning in a way that is completely different from traditional theorems.
Proceedings ArticleDOI
Efficient Knowledge Distillation from an Ensemble of Teachers.
TL;DR: It is shown that with knowledge distillation, information from multiple acoustic models like very deep VGG networks and Long Short-Term Memory models can be used to train standard convolutional neural network (CNN) acoustic models for a variety of systems requiring a quick turnaround.
Posted Content
NISP: Pruning Networks using Neuron Importance Score Propagation
Ruichi Yu,Ang Li,Chun-Fu Chen,Jui-Hsin Lai,Vlad I. Morariu,Xintong Han,Mingfei Gao,Ching-Yung Lin,Larry S. Davis +8 more
TL;DR: The Neuron Importance Score Propagation (NISP) algorithm is proposed to propagate the importance scores of final responses to every neuron in the network and is evaluated on several datasets with multiple CNN models and demonstrated to achieve significant acceleration and compression with negligible accuracy loss.
Posted Content
From Facial Parts Responses to Face Detection: A Deep Learning Approach
TL;DR: A novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW, and it is shown that despite the use of DCN, the network can achieve practical runtime speed.
Journal ArticleDOI
Text summarization using unsupervised deep learning
Mahmood Yousefi-Azar,Len Hamey +1 more
TL;DR: Experiments show that the AE using local vocabularies clearly provide a more discriminative feature space and improves the recall on average 11.2%, and the ENAE can make further improvements, particularly in selecting informative sentences.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Journal ArticleDOI
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Geoffrey E. Hinton,Li Deng,Dong Yu,George E. Dahl,Abdelrahman Mohamed,Navdeep Jaitly,Andrew W. Senior,Vincent Vanhoucke,Patrick Nguyen,Tara N. Sainath,Brian Kingsbury +10 more
TL;DR: This article provides an overview of progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
Posted Content
Improving neural networks by preventing co-adaptation of feature detectors
TL;DR: The authors randomly omits half of the feature detectors on each training case to prevent complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors.
Book ChapterDOI
Ensemble Methods in Machine Learning
TL;DR: Some previous studies comparing ensemble methods are reviewed, and some new experiments are presented to uncover the reasons that Adaboost does not overfit rapidly.