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
Proceedings ArticleDOI
Efficient Oct Image Segmentation Using Neural Architecture Search
Saba Heidari Gheshlaghi,Omid Dehzangi,Ali Dabouei,Annahita Amireskandari,Ali R. Rezai,Nasser M. Nasrabadi +5 more
TL;DR: The experimental results demonstrate that the self-adapting NAS-Unet architecture substantially outperformed the competitive human-designed architecture by achieving 95.4% in mean Intersection over Union metric and 78.7% in Dice similarity coefficient.
Posted Content
Exploiting Operation Importance for Differentiable Neural Architecture Search
TL;DR: A novel indicator is proposed that can fully represent the operation importance and serve as an effective metric to guide the model search and a high-order Markov chain-based strategy to slim the search space to further improve search efficiency and accuracy is proposed.
Journal ArticleDOI
Predicting atmospheric optical properties for radiative transfer computations using neural networks.
Menno A. Veerman,Robert Pincus,Robert Pincus,Robin Stoffer,Caspar van Leeuwen,Damian Podareanu,Chiel C. van Heerwaarden +6 more
TL;DR: It is concluded that a machine learning-based parametrization can speed-up radiative transfer computations while retaining high accuracy, and is up to four times faster than RRTMGP, depending on the size of the neural networks.
Proceedings ArticleDOI
Automated problem identification: regression vs classification via evolutionary deep networks
TL;DR: This paper proposed an evolutionary deep learning (EDL) algorithm that automatically solves the question type with high accuracy, along with a proposed deep architecture, and achieved an average accuracy of 96.3% in identifying the problem type.
Proceedings ArticleDOI
Pareto-optimal progressive neural architecture search
TL;DR: POPNAS as discussed by the authors combines the benefits of PNAS to a time-accuracy Pareto optimization problem by adding a new time predictor to the existing approach to carry out a joint prediction of time and accuracy for each candidate neural network.
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.