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
Evaluating the effectiveness of efficient neural architecture search for sentence-pair tasks
Ansel MacLaughlin,Jwala Dhamala,Anoop Kumar,Sriram Venkatapathy,Ragav Venkatesan,Rahul Gupta +5 more
TL;DR: The applicability of a SOTA NAS algorithm, Efficient Neural Architecture Search (ENAS) to two sentence pair tasks, paraphrase detection and semantic textual similarity is explored and results are mixed.
QueryNet: Attack by Multi-Identity Surrogates
TL;DR: QueryNet is developed, a unified attack framework that can significantly reduce queries in adversarial attacks by multi-identity surrogates and crafts several AEs for one sample by different surrogates, and also uses surrogates to decide on the most promising AE for the query.
Posted Content
New Perspective of Interpretability of Deep Neural Networks
Masanari Kimura,Masayuki Tanaka +1 more
TL;DR: In this paper, the human predictability of DNNs is defined as easiness to predict the change of the inference when perturbations are applied to the model of the DNN.
Journal ArticleDOI
Selecting and Composing Learning Rate Policies for Deep Neural Networks
Yanzhao Wu,Ling Liu +1 more
TL;DR: Evaluated using popular benchmark datasets and different DNN models, this approach can effectively deliver high DNN test accuracy, outperform the existing recommended default LR policies, and reduce the DNN training time by 1.6 ∼ 6.7 × to meet a targeted model accuracy.
Book ChapterDOI
Edge-Wise One-Level Global Pruning on NAS Generated Networks.
TL;DR: In this paper, an edge-wise one-level global pruning (EOG-Pruning) algorithm is proposed to prune out weak edges from the cell-based network generated by NAS globally, by introducing an edge factor to represent the importance of each edge.
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.