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
Proceedings Article
Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay
Haiyan Yin,Sinno Jialin Pan +1 more
TL;DR: A new policy distillation architecture for deep reinforcement learning is proposed, where it is assumed that each task uses its taskspecific high-level convolutional features as the inputs to the multi-task policy network.
Proceedings ArticleDOI
Lightweight Face Recognition Challenge
TL;DR: Two large-scale datasets are proposed and an extensive comparison metric is defined for an unbiased evaluation of deep face recognition models and each track has strict constraints on computational complexity and model size to ensure fair comparison during competition.
Proceedings ArticleDOI
Interpret Neural Networks by Identifying Critical Data Routing Paths
TL;DR: The Distillation Guided Routing method is developed, which is a flexible framework to interpret a deep neural network by identifying critical data routing paths and analyzing the functional processing behavior of the corresponding layers by learning associated control gates for each layer's output channel.
Proceedings ArticleDOI
Few-Shot Class-Incremental Learning
TL;DR: In this paper, the authors proposed the TOpology-preserving knowledge preserving knowledge InCrementer (TOPIC) framework to improve the representation learning for few-shot new classes by growing and adapting NG to new training samples.
Proceedings Article
Reward augmented maximum likelihood for neural structured prediction
Mohammad Norouzi,Samy Bengio,Zhifeng Chen,Navdeep Jaitly,Mike Schuster,Yonghui Wu,Dale Schuurmans +6 more
TL;DR: The authors proposed reward augmented maximum likelihood (RML), where the rewards are defined as the negative edit distance between the outputs and the ground truth labels, and the conditional log-probability of augmented outputs are sampled proportionally to their exponentiated scaled rewards.
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.