Open AccessPosted Content
Neural Architecture Search with Reinforcement Learning
Barret Zoph,Quoc V. Le +1 more
Reads0
Chats0
TLDR
This paper uses a recurrent network to generate the model descriptions of neural networks and trains this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set.Abstract:
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.read more
Citations
More filters
Journal ArticleDOI
Neural Architecture Search Survey: A Hardware Perspective
TL;DR: Hardware-Aware Neural Architecture Search (HW-NAS) automates the architectural design process of DNNs to alleviate human effort, and generate efficient models accomplishing acceptable accuracy-performance tradeoffs.
Posted Content
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
TL;DR: This work proposes MixMix based on two simple yet effective techniques, which outperforms existing methods on the mainstream compression tasks, including quantization, knowledge distillation and pruning, and proves the effectiveness of MixMix from both theoretical and empirical perspectives.
Proceedings ArticleDOI
Quantum-Inspired Neural Architecture Search
TL;DR: Q-NAS (Quantum-inspired Neural Architecture Search): a quantum-inspired algorithm to search for deep neural architectures by assembling substructures and optimizing some numerical hyperparameters that achieves promising accuracies with considerably less computational cost than other NAS algorithms.
Journal ArticleDOI
Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019
Zhengying Liu,Adrien Pavao,Zhen Xu,Sergio Escalera,Fabio Ferreira,Isabelle Guyon,Sirui Hong,Frank Hutter,Rongrong Ji,Julio C. S. Jacques Junior,Ge Li,Marius Lindauer,Luo Zhipeng,Meysam Madadi,Thomas Nierhoff,Kangning Niu,Chunguang Pan,Danny Stoll,Sebastien Treguer,Jin Wang,Peng Wang,Chenglin Wu,Youcheng Xiong,Arber Zela,Yang Zhang +24 more
TL;DR: This paper reports the results and post-challenge analyses of ChaLearn’s AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair comparisons.
Journal ArticleDOI
One-dimensional convolutional neural network-based active feature extraction for fault detection and diagnosis of industrial processes and its understanding via visualization.
TL;DR: In this paper, a one-dimension convolution neural network-based model optimized by a reinforcement-learning-based neural architecture search was proposed for multivariate process control, and the experimental results illustrate its predominance for detecting and recognizing process faults.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.