Posted Content•
Neural Architecture Search with Reinforcement 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
19 Jul 2020
TL;DR: This paper applies the randomness-enhanced tabu algorithm as a controller to sample candidate architectures, which balances the global exploration and local exploitation for the architectural solutions, and discovers the recurrent neural architecture within 0.78 GPU hour.
Abstract: Deep neural networks have achieved highly competitive performance in multiple tasks in recent years. However, discovering state-of-the-art neural network architectures requires substantial effort from human experts. To speed up the process, neural architecture search (NAS) has been proposed to search promising architectures automatically. Nevertheless, the search process of NAS is computing-expensive and time-consuming, which even costs thousands of GPU days. In this paper, to solve the bottleneck, we apply the randomness-enhanced tabu algorithm as a controller to sample candidate architectures, which balances the global exploration and local exploitation for the architectural solutions. In addition, more aggressive weight-sharing strategy is introduced into our method, which significantly reduces the overhead of evaluating sampled architectures. Our approach discovers the recurrent neural architecture within 0.78 GPU hour, which is 15.3x more efficient than ENAS [1] in terms of search time, and the architecture we discovered achieves the test perplexity of 56.1 on Penn Tree Bank (PTB) dataset, which is lower than ENAS by 2.2. In addition, we further demonstrate the usefulness of the learned architecture by transferring it to wiki-text-2 (WT2) dataset well. Moreover, the extended experiments on the WT2 dataset also show promising results.
3 citations
Cites background or methods or result from "Neural Architecture Search with Rei..."
...Surprisingly, NAS often breaks through the limitations of human minds and achieves unexpected results [1], [5], [6], [7], [8]....
[...]
...Zoph & Le [6] firstly presented modern algorithm automating architecture design, and resulting architectures can indeed outperform manually designed state-of-the-art neural networks....
[...]
...Similar to [6], some works [5], [13], [14] used reinforcement learning for neural architecture search, which formulate neural architecture search (NAS) as a graph search problem....
[...]
...NAS was first proposed by Zoph & Le [6]....
[...]
...Similar to [6], ENAS also uses reinforcement learning [9] to train the LSTM [10] controller to sample candidate architectures....
[...]
Posted Content•
TL;DR: This paper argues for the necessity of studying the landscape property of NAS and proposes to use the so-called Exploratory Landscape Analysis (ELA) techniques for this goal, taking a broad set of designs of the deep convolutional network.
Abstract: Neural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests. Despite various successful approaches proposed to solve the NAS task, the landscape of it, along with its properties, are rarely investigated. In this paper, we argue for the necessity of studying the landscape property thereof and propose to use the so-called Exploratory Landscape Analysis (ELA) techniques for this goal. Taking a broad set of designs of the deep convolutional network, we conduct extensive experimentation to obtain their performance. Based on our analysis of the experimental results, we observed high similarities between well-performing architecture designs, which is then used to significantly narrow the search space to improve the efficiency of any NAS algorithm. Moreover, we extract the ELA features over the NAS landscapes on three common image classification data sets, MNIST, Fashion, and CIFAR-10, which shows that the NAS landscape can be distinguished for those three data sets. Also, when comparing to the ELA features of the well-known Black-Box Optimization Benchmarking (BBOB) problem set, we found out that the NAS landscapes surprisingly form a new problem class on its own, which can be separated from all $24$ BBOB problems. Given this interesting observation, we, therefore, state the importance of further investigation on selecting an efficient optimizer for the NAS landscape as well as the necessity of augmenting the current benchmark problem set.
3 citations
Cites methods from "Neural Architecture Search with Rei..."
..., random search [17], Bayesian optimization [8], evolutionary methods [28], and reinforcement learning [33]....
[...]
Posted Content•
TL;DR: A unified approach to describing CNN architectures based on text, named ArcTxt, is proposed, to bridge the gap between CNN and data mining researchers, and has the potentiality to be utilized to wider scenarios.
Abstract: The superiority of Convolutional Neural Networks (CNNs) largely relies on their architectures that are often manually crafted with extensive human expertise. Unfortunately, such kind of domain knowledge is not necessarily owned by each of the users interested. Data mining on existing CNN can discover useful patterns and fundamental sub-comments from their architectures, providing researchers with strong prior knowledge to design proper CNN architectures when they have no expertise in CNNs. There have been various state-of-the-art data mining algorithms at hand, while there is only rare work that has been done for the mining. One of the main reasons is the gap between CNN architectures and data mining algorithms. Specifically, the current CNN architecture descriptions cannot be exactly vectorized to the input of data mining algorithms. In this paper, we propose a unified approach, named ArcText, to describing CNN architectures based on text. Particularly, four different units and an ordering method have been elaborately designed in ArcText, to uniquely describe the same architecture with sufficient information. Also, the resulted description can be exactly converted back to the corresponding CNN architecture. ArcText bridges the gap between CNN architectures and data mining researchers, and has the potentiality to be utilized to wider scenarios.
3 citations
Cites methods from "Neural Architecture Search with Rei..."
...For example, a reinforcement learning-based NAS method [11] consumed 28 days using 800 Graphics Processing Units (GPUs), and the large-scale evolution NAS method [12] employed 250 GPUs over 11 days....
[...]
TL;DR: Experimental results show that the proposed ANAO model can optimize the CNN architecture to adaptively fit a given dataset and achieve quite high-level performance.
3 citations
TL;DR: Reference Point Based Neural Architecture Search (RNSGA-Net) as mentioned in this paper adopts the reference point approach to guarantee the Pareto-optimal region close to the reference points and also combines the advantage of NSGAII with the fast nondominated sorting approach to split the pareto front.
3 citations
References
More filters
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 2015TL;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 2014TL;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)....
[...]
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
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)....
[...]