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
Reliability‐aware service chaining mapping in NFV‐enabled networks
TL;DR: A mixed integer linear programming formulation is provided to address this problem along with a novel online algorithm that adopts the joint protection redundancy model and novel backup selection scheme and the results show that the proposed algorithm can significantly improve the request acceptance ratio and reduce the consumption of physical resources compared to existing backup algorithms.
Proceedings ArticleDOI
CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS
TL;DR: Curriculum Learning On Sharing Extent is proposed, which can obtain a better ranking quality across different computational budget constraints than other one-shot supernets, and is able to discover superior architectures when combined with various search strategies.
Journal ArticleDOI
EtinyNet: Extremely Tiny Network for TinyML
TL;DR: There are many AI applications in high-income countries because their implementation depends on expensive GPU cards and reliable power supply, so it is important to deploy AI in resource-poor settings on cheaper and low-power devices.
Journal ArticleDOI
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning
TL;DR: In this article , the authors attempt to explain the confusing state of network pruning by demystifying the two mysteries, namely the performance boosting effect of a larger finetuning learning rate and the no-value argument of inheriting pretrained weights in filter pruning.
Journal ArticleDOI
Comparative analysis of image projection-based descriptors in Siamese neural networks
TL;DR: In this paper, a backtracking search-based Neural Architecture Generation method is used to create convolutional architectures, and a Master/Worker structured distributed processing with highly efficient scheduling based on the Longest Processing Times-heuristics is used for parallel training and evaluation of the models.
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.