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
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
TL;DR: TE-NAS as discussed by the authors ranks architectures by analyzing the spectrum of the neural tangent kernel and the number of linear regions in the input space, which can be computed without any training and any label.
Proceedings ArticleDOI
NAX: neural architecture and memristive xbar based accelerator co-design
TL;DR: NAX is proposed - an efficient neural architecture search engine that co-designs neural network and IMC based hardware architecture and explores the aforementioned search space to determine kernel and corresponding crossbar sizes for each DNN layer to achieve optimal tradeoffs between hardware efficiency and application accuracy.
Proceedings Article
Searching for BurgerFormer with Micro-Meso-Macro Space Design
TL;DR: Xing et al. as mentioned in this paper designed a micro-meso-macro space to search for Transformer-like architectures, namely Burgerformer, which enriched the atomic operations to include various normalizations, activation functions, and basic operations (e.g., multi-head self attention, average pooling).
Journal ArticleDOI
Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment
TL;DR: This work forms NAS tasks into general multi-objective optimization problems and analyzes the complex characteristics from an optimization point of view, and presents an end-to-end pipeline, dubbed EvoXBench, to generate benchmark test problems for EMO algorithms to run without the requirement of GPUs or Pytorch/TensorFlow.
Journal Article
Deep Reinforcement Learning: Opportunities and Challenges
TL;DR: In this article, a brief introduction to reinforcement learning (RL), and its relationship with deep learning, machine learning and AI is given, and a discussion is attempted, attempting to answer: “Why has RL not been widely adopted in practice yet?” and “When is RL helpful?’.
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.