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
Towards More Efficient EfficientDets and Real-Time Marine Debris Detection
TL;DR: In this paper , the authors focus on the efficiency of AUV vision for real-time marine debris detection and use it to detect in-water plastic bags and bottles and train a class of state-of-the-art object detectors.
Journal ArticleDOI
Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
TL;DR: This paper is the first to provide a convergence-provable framework that enables free-form DNNs in ISTA-based unfolded algorithms and can reduce the reconstruction error with an improved convergence rate in the tasks of sparse recovery and compressive sensing.
Journal ArticleDOI
Taekwondo Action Recognition Method Based on Partial Perception Structure Graph Convolution Framework
Jianqiao Liang,Guocai Zuo +1 more
TL;DR: A graph convolution framework with part of the perception structure to recognize, decompose, and analyze Taekwondo actions and has an average accuracy of 90% in action recognition, and an average action score matching rate of 74.6%.
Posted Content
You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient.
Shaokun Zhang,Xiawu Zheng,Chenyi Yang,Yuchao Li,Yan Wang,Fei Chao,Mengdi Wang,Shen Li,Jun Yang,Rongrong Ji +9 more
TL;DR: YOCO-BERT as mentioned in this paper proposes a novel stochastic nature gradient optimization method to guide the generation of optimal candidate architecture which could keep a balanced trade-off between explorations and exploitation.
Journal ArticleDOI
MOO-DNAS: Efficient Neural Network Design via Differentiable Architecture Search Based on Multi-Objective Optimization
TL;DR: An efficient CNN architecture search framework, MOO-DNAS, with multi-objective optimization based on differentiable neural architecture search, and a robust sampling strategy named “hard-sampling” is proposed to obtain final structures with higher average performance by keeping the highest scoring operator.
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.