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
Meta-Meta-Classification for One-Shot Learning.
TL;DR: The meta-meta learning approach is shown to be able to outperform traditional meta-learning as well as ensembling approaches on a one-shot, one-class-versus-all classification task.
Journal ArticleDOI
NAS-FCOS: Efficient Search for Object Detection Architectures
TL;DR: Lausannen et al. as discussed by the authors proposed an efficient method to obtain better object detectors by searching for the feature pyramid network as well as the prediction head of a simple anchor-free object detector, namely, FCOS, using a tailored reinforcement learning paradigm.
Journal ArticleDOI
FocusFormer: Focusing on What We Need via Architecture Sampler
TL;DR: A simple yet effective method, called FocusFormer, to learn an architecture sampler to assign higher sampling probabilities to those architectures on the Pareto frontier under different resource constraints during supernet training, making them sufficiently optimized and hence improving their performance.
Journal Article
Meta-learning Transferable Representations with a Single Target Domain
TL;DR: Meta Representation Learning (MeRLin) is proposed to learn transferable features and empirically outperforms previous state-of-the-art transfer learning algorithms on various real-world vision and NLP transfer learning benchmarks.
Journal ArticleDOI
CURIOUS: Efficient Neural Architecture Search Based on a Performance Predictor and Evolutionary Search
TL;DR: The CURIOUS NN synthesis methodology uses a performance predictor to efficiently navigate the architectural search space with an evolutionary search process and obtains the highest accuracy for various other FFNNs that are geared toward edge devices and IoT sensors.
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.