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
Posted Content
TL;DR: In this paper, the authors proposed a pre-training scheme that leverages the structural similarity of network architectures to obtain good architecture representations and incorporated the method into neural architecture optimization (NAO) to analyze the pretrained embeddings and its effectiveness.
Abstract: Neural architecture search (NAS) has fostered various fields of machine learning. Despite its prominent dedications, many have criticized the intrinsic limitations of high computational cost. We aim to ameliorate this by proposing a pretraining scheme that can be generally applied to controller-based NAS. Our method, locality-based self-supervised classification task, leverages the structural similarity of network architectures to obtain good architecture representations. We incorporate our method into neural architecture optimization (NAO) to analyze the pretrained embeddings and its effectiveness and highlight that adding metric learning loss brings a favorable impact on NAS. Our code is available at \url{this https URL}.

1 citations

DOI
01 Jan 2020
TL;DR: This research attacked the mode confusion problem by developing a modeling framework to describe human interaction with mode-based learning systems and found a number of mechanisms to be Turing-complete.
Abstract: DYNAMIC COMPOSITION OF FUNCTIONS FOR MODULAR LEARNING

1 citations


Additional excerpts

  • ...The first research along this line was a very straightforward search utilizing reinforcement learning: Construct an architecture, train it until convergence, evaluate its performance and use that (accuracy) score as a reward, then repeat [Zoph and Le, 2017, Baker et al., 2017]....

    [...]

Proceedings ArticleDOI
14 Jul 2019
TL;DR: The reinforcement learning method is used to search for networks offline, with both high accuracy and small network size, and the network generated by this method is competitive with other methods on Cifar-10.
Abstract: Neural networks with both high accuracy and small network size are urgently required for mobile phone applications. However, previous network search methods do not take network size into account. In this paper, we use the reinforcement learning method to search for networks offline, with both high accuracy and small network size. Gaussian policy is used to explore the number of convolutional channels in a finer manner. Parameter reward is included in our reward function to punish large networks. We also use binary networks to further reduce network size. Without skip connections or branches, the network generated by our method is competitive with other methods on Cifar-10. Our network is much smaller than networks generated by other network search methods. Besides, our accuracy is higher than original binary network reported in BinaryConnect and is competitive with other real-valued networks.

1 citations


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

  • ...Some works use policy gradient algorithm to design networks [4], [9], [10]....

    [...]

  • ...Different from NAS [4], we use Gaussian policy to predict the number of channels....

    [...]

  • ...Besides, our method is faster than NAS [4], MetaQNN [5] and EAS [10]....

    [...]

  • ...Compared with softmax policy (as shown in (9)) used in [4], [5], [9], Gaussian policy has several advantages....

    [...]

  • ...For policy gradient methods in [4], [9], [10], the number of channels is fixed to several pre-defined numbers and is predicted through discrete softmax policy....

    [...]

Posted Content
TL;DR: In this article, the authors present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge.
Abstract: Creating photorealistic materials for light transport algorithms requires carefully fine-tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge. In the proposed workflow, the user starts with an input image and applies a few intuitive transforms (e.g., colorization, image inpainting) within a 2D image editor of their choice, and in the next step, our technique produces a photorealistic result that approximates this target image. Our method combines the advantages of a neural network-augmented optimizer and an encoder neural network to produce high-quality output results within 30 seconds. We also demonstrate that it is resilient against poorly-edited target images and propose a simple extension to predict image sequences with a strict time budget of 1-2 seconds per image.

1 citations

Proceedings ArticleDOI
01 Jan 2022
TL;DR: This paper introduces a new approach to analyze images using AI tools, resulting in data that can assess representation of race, gender, and age in both illustrations and photographs in children’s books and examines distributions of character identities over the last century across the models.
Abstract: Images in children’s books convey messages about society and the roles that people play in it. Understanding these messages requires systematic measurement of who is represented. Computer vision face detection tools can provide such measurements; however, state-of-the-art face detection models were trained with photographs, and 80% of images in children’s books are illustrated; thus existing methods both misclassify and miss classifying many faces. In this paper, we introduce a new approach to analyze images using AI tools, resulting in data that can assess representation of race, gender, and age in both illustrations and photographs in children’s books. We make four primary contributions to the fields of deep learning and social sciences: (1) We curate an original face detection data set (IllusFace 1.0) by manually labeling 5,403 illustrated faces with bounding boxes. (2) We train two AutoML-based face detection models for illustrations: (i) using IllusFace 1.0 (FDAI); (ii) using iCartoon, a publicly available data set (FDAI iC), each optimized for illustrated images, detecting 2.5 times more faces in our testing data than the established face detector using Google Vision (FDGV). (3) We curate a data set of the race, gender, and age of 980 faces manually labeled by three different raters (CBFeatures 1.0). (4) We train an AutoML feature classification model (FCA) using CBFeatures 1.0. We compare FCA with the performance of another AutoML model that we trained on UTKFace, a public data set (FCA UTK) and of an established model using FairFace (FCF). Finally, we examine distributions of character identities over the last century across the models. We find that FCA is 34% more accurate than FCF in its race predictions. These contributions provide tools to educators, caregivers, and curriculum developers to assess the representation contained in children’s content.

1 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)....

    [...]