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
Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation
TL;DR: This paper introduces imitation learning (IL) with optimal paths to optimize navigation policies while selecting an optimal architecture in neural architecture search, and proposes an Auto-Navigator to customize a specialized network for visual navigation.
Posted Content
TimeGate: Conditional Gating of Segments in Long-range Activities
TL;DR: TimeGate reduces the computation of existing CNNs on three benchmarks for long-range activities: Charades, Breakfast and MultiThumos and reduces the computations of I3D by 50% while maintaining the classification accuracy.
Posted Content
HyperSTAR: Task-Aware Hyperparameters for Deep Networks
TL;DR: This work presents HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks, and demonstrates that HyperSTAR makes Hyperband (HB) task- Aware, achieving the optimal accuracy in just 25% of the budget required by both vanilla HB and Bayesian Optimized HB.
Journal ArticleDOI
Estimating visual field loss from monoscopic optic disc photography using deep learning model
Jinho Lee,Jinho Lee,Yong Woo Kim,Yong Woo Kim,Ahnul Ha,Ahnul Ha,Young Kook Kim,Young Kook Kim,Ki Ho Park,Ki Ho Park,Hyuk Jin Choi,Hyuk Jin Choi,Jin Wook Jeoung,Jin Wook Jeoung +13 more
TL;DR: A deep learning algorithm that quantitatively predicts mean deviation (MD) of standard automated perimetry (SAP) from monoscopic optic disc photographs (ODPs) showed great feasibility for prediction of MD and detection of glaucomatous functional loss from ODPs.
Journal ArticleDOI
An experimental analysis of different Deep Learning based Models for Alzheimer’s Disease classification using Brain Magnetic Resonance Images
TL;DR: In this article, the authors proposed to replace the convolution layers in the original DenseNet-121 architecture with depth-wise convolution, which improved the performance of the model with an average rate of 90.22%.
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.