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
Auto Whole Heart Segmentation from CT images Using an Improved Unet-GAN
TL;DR: A new network architecture based on a traditional architecture called conditional generative adversarial network (cGAN), where R2U-Net acts as the generative network and FCN as the discriminative network is proposed.
Posted Content
CompConv: A Compact Convolution Module for Efficient Feature Learning
Chen Zhang,Yinghao Xu,Yujun Shen +2 more
TL;DR: This work makes a close study of the convolution operator, which is the basic unit used in CNNs, to reduce its computing load and proposes a compact convolution module, called CompConv, to facilitate efficient feature learning.
Posted Content
IndyLSTMs: Independently Recurrent LSTMs.
Pedro Gonnet,Thomas Deselaers +1 more
TL;DR: Independently Recurrent Long Short-Term Memory (Independent LSTM) as mentioned in this paper models the weights as a diagonal matrix, i.e. the output and state of each layer depends on the inputs and its own output/state, as opposed to the input and the outputs/state of all the cells in the layer.
Journal ArticleDOI
Towards automated computer vision: analysis of the AutoCV challenges 2019
Zhengying Liu,Zhen Xu,Zhen Xu,Sergio Escalera,Isabelle Guyon,Julio C. S. Jacques Junior,Meysam Madadi,Adrien Pavao,Sebastien Treguer,Wei-Wei Tu +9 more
TL;DR: The results of recent challenges in Automated Computer Vision (AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning (AutoDL), aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance.
Posted ContentDOI
A Framework for Designing Efficient Deep Learning-Based Genomic Basecallers
Gagandeep Singh,Mohammed Alser,Ali Khodamoradi,Kristof Denolf,Can Fırtına,Meryem Banu Cavlak,Henk Corporaal,Onur Mutlu +7 more
TL;DR: Zhang et al. as mentioned in this paper proposed a quantization-aware base calling neural architecture search (QABAS) framework to find the best bit-width precision for each neural network layer.
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.