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
Posted Content
Neural Architecture Search with GBDT.
TL;DR: This paper proposes to leverage gradient boosting decision tree (GBDT) as the predictor for NAS and demonstrates that it can improve the prediction accuracy and help to find better architectures than neural network based predictors.
Book ChapterDOI
CAVE: Configuration Assessment, Visualization and Evaluation
TL;DR: CAVE aims to help algorithm and configurator developers to better understand their experimental setup in an automated fashion by providing a tool that automatically generates comprehensive reports and insightful figures from all available empirical data.
Posted ContentDOI
Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping
TL;DR: In both tasks, AutoKeras generated compact CNN models with up to 40-fold faster inference times compared to the pretrained CNNs, and the merits and drawbacks of AutoML compared to transfer learning for image-based plant phenotyping are discussed.
Posted Content
TF-Coder: Program Synthesis for Tensor Manipulations
TL;DR: TF-Coder is presented, a tool for programming by example in TensorFlow that uses a bottom-up weighted enumerative search, with value- based pruning of equivalent expressions and flexible type- and value-based filtering to ensure that expressions adhere to various requirements imposed by the Tensor Flow library.
Proceedings ArticleDOI
Where to prune: using LSTM to guide end-to-end pruning
TL;DR: This paper argues that the pruning order is also very significant for model pruning, and proposes a novel approach to figure out which layers should be pruned in each step, utilizing a long short-term memory to learn the hierarchical characteristics of a network and generate a pruning decision for each layer.
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.