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
Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization.
Panjie Qi,Edwin H.-M. Sha,Qingfeng Zhuge,Hongwu Peng,Shaoyi Huang,Zhenglun Kong,Yuhong Song,Bingbing Li +7 more
TL;DR: Li et al. as discussed by the authors proposed an algorithm and hardware closed-loop acceleration framework to solve the deployment challenge of Transformer and the problem to select the best device, given a dataset, a model, latency constraint LC and accuracy constraint AC, their framework can provide a best device satisfying both constraints.
Proceedings ArticleDOI
Optimizing FPGA-Based CNN Accelerator Using Differentiable Neural Architecture Search
TL;DR: In this paper, a novel FPGA-based CNN accelerator is proposed and an accurate performance model of the proposed hardware design is also introduced, and the authors then apply DNAS and encapsulate the proposed performance model into the objective function.
Posted Content
Evolutionary Neural Architecture Search for Retinal Vessel Segmentation
TL;DR: A novel approach which applies neural architecture search (NAS) to optimize an encoder-decoder architecture for retinal vessel segmentation achieves top performance among all compared methods on the three datasets, namely DRIVE, STARE and CHASE_DB1, but with much fewer parameters.
Journal ArticleDOI
Evaluating representational systems in artificial intelligence
John Licato,Zhitian Zhang +1 more
TL;DR: This work surveys the criteria that are used for evaluations in AI, machine learning, and other AI-related fields and introduces a formalism of representations, representational systems, and representational spaces that lends itself nicely to an analysis of the criteria typically used for evaluating them.
Journal ArticleDOI
DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization
Chaoli Wang,Jun Han +1 more
TL;DR: This state-of-the-art survey of deep learning works in SciVis guides SciVis researchers in gaining an overview of this emerging topic and points out future directions to grow this research.
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.