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 ArticleDOI
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
TL;DR: A novel teacher-student approach for the multi-hop KBQA task, where the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network, and both forward and backward reasoning are utilized to enhance the learning of intermediate entity distributions.
Posted Content
Distilling Dense Representations for Ranking using Tightly-Coupled Teachers.
TL;DR: This work distill the knowledge from ColBERT's expressive MaxSim operator for computing relevance scores into a simple dot product, thus enabling single-step ANN search and improves query latency and greatly reduces the onerous storage requirements of ColberT.
Posted Content
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
TL;DR: This work generalizes the theory to the case of unknown intrinsic problem dimension and proves that in some special (but not very restrictive) cases, informative latent variables will be automatically separated from noise by an estimating model.
Posted Content
Network Pruning via Transformable Architecture Search
Xuanyi Dong,Yi Yang +1 more
TL;DR: In this paper, the authors proposed to apply neural architecture search to search directly for a network with flexible channel and layer sizes, where the number of channels/layers is learned by minimizing the loss of the pruned networks.
Proceedings ArticleDOI
Edge Intelligence: Challenges and Opportunities of Near-Sensor Machine Learning Applications
TL;DR: It is argued that for a wide range of emerging applications edge intelligence is a necessary evolutionary need, and thus a summary of the challenges and opportunities that arise from this need is provided.
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.