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
10 Jan 2021
TL;DR: DeCoNASNet as discussed by the authors uses a hierarchical search strategy to find the best connection with local and global features, which can be considered a multi-objective problem and outperforms the state-of-the-art lightweight super-resolution networks designed by handcraft methods and existing NAS-based design.
Abstract: The recent progress of deep convolutional neural networks has enabled great success in single image super-resolution (SISR) and many other vision tasks. Their performances are also being increased by deepening the networks and developing more sophisticated network structures. However, finding an optimal structure for the given problem is a difficult task, even for human experts. For this reason, neural architecture search (NAS) methods have been introduced, which automate the procedure of constructing the structures. In this paper, we expand the NAS to the super-resolution domain and find a lightweight densely connected network named DeCoNASNet. We use a hierarchical search strategy to find the best connection with local and global features. In this process, we define a complexity-based penalty for solving image super-resolution, which can be considered a multi-objective problem. Experiments show that our DeCoNASNet outperforms the state-of-the-art lightweight super-resolution networks designed by handcraft methods and existing NAS-based design.
8 citations
01 Dec 2018
TL;DR: The challenge protocol and baseline results are presented to seek community feed-back and drive the community to work on finding fully automatic ways of designing DL models.
Abstract: Following the success of the first AutoML challenges , we designed a new challenge called AutoDL. We target applications such as speech, image, video, and text, for which deep learning (DL) methods have had great success in the past few years. All problems will be multi-label classification problems. We hope to drive the community to work on finding fully automatic ways of designing DL models. Raw data will be provided (no features extracted). The source of the datasets and the type of data will be concealed, but the data structure will be revealed. All datasets will be formatted in a uniform tensor manner, to encourage participants to submit generic algorithms (not necessarily constrained to DL). We will impose restrictions on training time and resources to push the state-of-the-art further. We will provide a large number of pre-formatted public datasets and set up a repository of data exchange to enable meta-learning. In this paper, the challenge protocol and baseline results are presented to seek community feed-back. The challenge is planned for 2019, but the exact schedule is not announced yet.
8 citations
Cites background from "Neural Architecture Search with Rei..."
...Lastly, ideas borrowed from reinforcement learning have recently been applied for this problem [24, 2]....
[...]
Proceedings Article•
05 Apr 20198 citations
TL;DR: This work innovatively utilize prior knowledge to convert architecture optimization problems into submodular optimization problems and proposes efficient Greedy algorithms to solve them and gives theoretical bounds of these algorithms.
Abstract: The architecture of convolutional neural networks (CNNs) is a key factor of influencing their performance. Although deep CNNs perform well in many difficult problems, how to intelligently design the architecture is still a challenging problem. Focusing on two practical architectural design problems: to maximize the accuracy with a given forward running time and to minimize the forward running time with a given accuracy requirement, we innovatively utilize prior knowledge to convert architecture optimization problems into submodular optimization problems. We propose efficient Greedy algorithms to solve them and give theoretical bounds of our algorithms. Specifically, we employ the techniques on some public data sets and compare our algorithms with some other hyperparameter optimization methods. Experiments show our algorithms’ efficiency.
8 citations
Cites background from "Neural Architecture Search with Rei..."
...For instance, Zoph and Le [10] take hundreds of GPUs at once and explore millions of architectures....
[...]
...Zoph and Le [10] use a recurrent network to generate convolutional architectures and Baker et al....
[...]
Posted Content•
TL;DR: This paper proposes a Neural Architecture Search (NAS) based framework to explore both architecture and parameter design space for automatic dataset-oriented LSM model, and adopts a three-step search for LSM, including multi-liquid architecture search, variation on the number of neurons and parameters search such as percentage connectivity and excitatory neuron ratio within each liquid.
Abstract: Liquid State Machine (LSM), also known as the recurrent version of Spiking Neural Networks (SNN), has attracted great research interests thanks to its high computational power, biological plausibility from the brain, simple structure and low training complexity. By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity. However, these works are based on manually-defined network architectures or predefined parameters. Considering the diversity and uniqueness of brain structure, the design of LSM model should be explored in the largest search space possible. In this paper, we propose a Neural Architecture Search (NAS) based framework to explore both architecture and parameter design space for automatic dataset-oriented LSM model. To handle the exponentially-increased design space, we adopt a three-step search for LSM, including multi-liquid architecture search, variation on the number of neurons and parameters search such as percentage connectivity and excitatory neuron ratio within each liquid. Besides, we propose to use Simulated Annealing (SA) algorithm to implement the three-step heuristic search. Three datasets, including image dataset of MNIST and NMNIST and speech dataset of FSDD, are used to test the effectiveness of our proposed framework. Simulation results show that our proposed framework can produce the dataset-oriented optimal LSM models with high accuracy and low complexity. The best classification accuracy on the three datasets is 93.2%, 92.5% and 84% respectively with only 1000 spiking neurons, and the network connections can be averagely reduced by 61.4% compared with a single LSM. Moreover, we find that the total quantity of neurons in optimal LSM models on three datasets can be further reduced by 20% with only about 0.5% accuracy loss.
8 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...[16], which automates the process of discovering promising neural architectures....
[...]
...The original NAS [16] learns an RNN controller to sample a better architecture....
[...]
...Neural Architecture Search (NAS) has achieved comparable performance to neural architectures by human experts in Recurrent Neural Network (RNN), Convolutional Neural Network (CNN) and even Graph Convolutional Network (GCN) [14], [15], [16]....
[...]
...Reinforcement learning (RL) [16] and evolutionary algorithms [17] are currently two mainstream methods to NAS....
[...]
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)....
[...]