Open AccessPosted Content
Neural Architecture Search with Reinforcement Learning
Barret Zoph,Quoc V. Le +1 more
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
Book ChapterDOI
Auto-Classifier: A Robust Defect Detector Based on an AutoML Head
Vasco Lopes,Luís A. Alexandre +1 more
TL;DR: It is shown that the use of Convolutional Neural Networks achieves better results than traditional methods, and also, that Auto-Classifier out-performs all other methods, by achieving 100% accuracy and 100% AUC results throughout all the datasets.
Journal ArticleDOI
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
TL;DR: The authors proposed AutoPEFT for automatic PEFT configuration selection, which first designs an expressive configuration search space with multiple representative PEFT modules as building blocks and then discovers a Pareto-optimal set of configurations with strong performance-cost trade-offs across different numbers of parameters that are also highly transferable across different tasks.
Proceedings ArticleDOI
ASBP: Automatic Structured Bit-Pruning for RRAM-based NN Accelerator
TL;DR: In this paper, the authors proposed an automatic structured bit-pruning design, ASBP, to harmonize the optimization objective of DNN sparsity with efficient RRAM deployment, which prunes the bits of weight which are split into different crossbars and free the zero-value crossbar when mapping the neural network into RRAM-based accelerators without extra hardware modification.
Posted Content
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
TL;DR: HardCoRe-NAS as mentioned in this paper is based on an accurate formulation of the expected resource requirement and a scalable search method that satisfies the hard constraint throughout the search, achieving state-of-the-art performance.
Journal Article
ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
TL;DR: This paper introduces a structural regularization across convolutional kernels in a CNN, and proposes models with sharing across different sub-structures to cover a wide range of trade-offs between parameter reduction and expressiveness.
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.