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
Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search
TL;DR: Field Programmable Gate Arrays (FPGAs) are used as a vehicle to present a novel hardware-aware NAS framework, namely FNAS, which will provide an optimal neural architecture with latency guaranteed to meet the specification and is the very first hardware aware NAS.
Book ChapterDOI
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
TL;DR: A novel lane-sensitive architecture search framework named CurveLane-NAS to automatically capture both long-ranged coherent and accurate short-range curve information while unifying both architecture search and post-processing on curve lane predictions via point blending.
Proceedings Article
AdaNet: adaptive structural learning of artificial neural networks
TL;DR: The results demonstrate that the AdaNet algorithm can automatically learn network structures with very competitive performance accuracies when compared with those achieved for neural networks found by standard approaches.
Journal ArticleDOI
SceneNet: Remote sensing scene classification deep learning network using multi-objective neural evolution architecture search
TL;DR: In this article, a framework for scene classification network architecture search based on multi-objective neural evolution (SceneNet) is proposed, and the effectiveness of SceneNet is demonstrated by experimental comparisons with several deep neural networks designed by human experts.
Posted Content
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
Dimitrios Stamoulis,Ruizhou Ding,Di Wang,Dimitrios Lymberopoulos,Bodhi Priyantha,Jie Liu,Diana Marculescu +6 more
TL;DR: Single-Path NAS as mentioned in this paper uses one single-path over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters, hence drastically decreasing the number of trainable parameters and the search cost down to few epochs.
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.