scispace - formally typeset
Search or ask a question
Posted Content

Neural Architecture Search with Reinforcement Learning

Barret Zoph1, Quoc V. Le1
05 Nov 2016-arXiv: Learning-
TL;DR: 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.
Citations
More filters
Journal ArticleDOI
TL;DR: In this article, an automated Bayesian inference framework, called AutoBayes, is proposed to learn disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels.
Abstract: Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores different graphical models linking classifier, encoder, decoder, estimator and adversarial network blocks to optimize nuisance-invariant machine learning pipelines. Auto Bayes also enables learning disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels. We benchmark the framework on several public datasets, and provide analysis of its capability for subject-transfer learning with/without variational modeling and adversarial training. We demonstrate a significant performance improvement with ensemble learning across explored graphical models.

4 citations

Book ChapterDOI
10 Jul 2019
TL;DR: This work proposes to use reinforcement learning to automatically design the network architecture and demonstrates that the proposed method can design an efficient and high-quality architecture for image inpainting.
Abstract: Neural Architecture Search (NAS) shows the ability to automate the architecture engineering for specific tasks recently which is extremely promising. Many published works apply reinforcement learning or evolutionary algorithm to design the neural architecture for image classification and achieve state-of-the-art performance. However, using NAS to perform other challenging tasks, such as inpainting irregular regions in an image, has not been explored yet. The target of image inpainting is to generate plausible image regions to fill the missing regions in the original image. It has been widely used in many applications. In this paper, we are interested in applying neural architecture search methods to image inpainting tasks. We propose to use reinforcement learning to automatically design the network architecture. Our method can efficiently explore new network structure based on existing architecture. The experiment result demonstrates that the proposed method can design an efficient and high-quality architecture for image inpainting.

4 citations

Posted Content
TL;DR: The approach finds the optimal neural architecture by dropping out candidate operations in an over-parameterised supergraph using variational dropout with automatic relevance determination prior, which makes the algorithm gradually remove unnecessary operations and connections without risking mode collapse.
Abstract: In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image classification or object detection. In particular, gradient-based NAS approaches have become one of the more popular approaches thanks to their computational efficiency during the search. However, these methods often experience a mode collapse, where the quality of the found architectures is poor due to the algorithm resorting to choosing a single operation type for the entire network, or stagnating at a local minima for various datasets or search spaces. To address these defects, we present a differentiable variational inference-based NAS method for searching sparse convolutional neural networks. Our approach finds the optimal neural architecture by dropping out candidate operations in an over-parameterised supergraph using variational dropout with automatic relevance determination prior, which makes the algorithm gradually remove unnecessary operations and connections without risking mode collapse. The evaluation is conducted through searching two types of convolutional cells that shape the neural network for classifying different image datasets. Our method finds diverse network cells, while showing state-of-the-art accuracy with up to almost 2 times fewer non-zero parameters.

4 citations


Cites background or methods from "Neural Architecture Search with Rei..."

  • ...Based on the core algorithmic principle operating during the search, NAS can be divided into four categories: (i) reinforcement learning-based on an actor-critic framework [1]...

    [...]

  • ...Current NAS methods are already able to automatically find better neural architectures, in comparison to hand-made NNs [1]–[3], [5]....

    [...]

  • ...I. INTRODUCTION Neural networks (NNs) have demonstrated their great potential in a wide range of artificial intelligence tasks such as image classification, object detection or speech recognition [1]–[3]....

    [...]

  • ...Additionally, all of the evaluated NNs shared the same evaluation hyperparameters and in the future we want to investigate an approach which can automatically determine suitable hyperparameters for the found architecture....

    [...]

  • ...Neural networks (NNs) have demonstrated their great potential in a wide range of artificial intelligence tasks such as image classification, object detection or speech recognition [1]–[3]....

    [...]

Posted Content
07 Oct 2020
TL;DR: This paper designs an expressive search space that focuses on a common and critical component of GNNs -- propagation model, and proposes a sampling-based one-shot NAS algorithm to search for appropriate propagation patterns efficiently.
Abstract: This paper presents a novel neural architecture search (NAS) framework for graph neural networks (GNNs). We design an expressive search space that focuses on a common and critical component of GNNs -- propagation model. Specifically, we search for propagation matrices and the connections between propagation steps. Our search space covers various graph types, e.g., homogeneous graphs, heterogeneous graphs, and can be naturally extended to higher-dimensional recommender systems and spatial-temporal data. We propose a sampling-based one-shot NAS algorithm to search for appropriate propagation patterns efficiently. Extensive experiments in three different scenarios are used to evaluate the proposed framework. We show that the performance of the models obtained by our framework is better than state-of-the-art GNN methods. Furthermore, our framework can discover explainable meta-graphs in heterogeneous graphs.

4 citations

Journal ArticleDOI
01 May 2022-Entropy
TL;DR: A novel deep architecture generation model based on Aquila optimization (AO) and a genetic algorithm (GA) so that the evolutionary computing algorithm can be combined with CNN and the experimental results show that the proposed model has good results in terms of search accuracy and time.
Abstract: Manually designing a convolutional neural network (CNN) is an important deep learning method for solving the problem of image classification. However, most of the existing CNN structure designs consume a significant amount of time and computing resources. Over the years, the demand for neural architecture search (NAS) methods has been on the rise. Therefore, we propose a novel deep architecture generation model based on Aquila optimization (AO) and a genetic algorithm (GA). The main contributions of this paper are as follows: Firstly, a new encoding strategy representing the CNN coding structure is proposed, so that the evolutionary computing algorithm can be combined with CNN. Secondly, a new mechanism for updating location is proposed, which incorporates three typical operators from GA cleverly into the model we have designed so that the model can find the optimal solution in the limited search space. Thirdly, the proposed method can deal with the variable-length CNN structure by adding skip connections. Fourthly, combining traditional CNN layers and residual blocks and introducing a grouping strategy provides greater possibilities for searching for the optimal CNN structure. Additionally, we use two notable datasets, consisting of the MNIST and CIFAR-10 datasets for model evaluation. The experimental results show that our proposed model has good results in terms of search accuracy and time.

4 citations

References
More filters
Proceedings ArticleDOI
27 Jun 2016
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.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

123,388 citations

Proceedings Article
01 Jan 2015
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.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

111,197 citations

Proceedings Article
04 Sep 2014
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.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

55,235 citations


"Neural Architecture Search with Rei..." refers methods in this paper

  • ...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....

    [...]

Journal ArticleDOI
01 Jan 1998
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.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

42,067 citations

Proceedings ArticleDOI
20 Jun 2005
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.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

31,952 citations


"Neural Architecture Search with Rei..." refers methods in this paper

  • ...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....

    [...]