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
Posted Content•
TL;DR: In this article, the authors propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network architecture, and they prove that the propagation in the feed-forward neural network with the same linear transformation in different layers is equivalent to minimizing some function using the gradient descent algorithm.
Abstract: Deep neural networks have been one of the dominant machine learning approaches in recent years. Several new network structures are proposed and have better performance than the traditional feedforward neural network structure. Representative ones include the skip connection structure in ResNet and the dense connection structure in DenseNet. However, it still lacks a unified guidance for the neural network structure design. In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network structure. Specifically, we prove that the propagation in the feedforward neural network with the same linear transformation in different layers is equivalent to minimizing some function using the gradient descent algorithm. Based on this observation, we replace the gradient descent algorithm with the heavy ball algorithm and Nesterov's accelerated gradient descent algorithm, which are faster and inspire us to design new and better network structures. ResNet and DenseNet can be considered as two special cases of our framework. Numerical experiments on CIFAR-10, CIFAR-100 and ImageNet verify the advantage of our optimization algorithm inspired structures over ResNet and DenseNet.
21 citations
TL;DR: This paper proposes a reconfiguration of the model parameters into several parallel branches at the global network level, with each branch being a standalone CNN, and shows that this arrangement is an efficient way to significantly reduce the number of parameters while at the same time improving the performance.
21 citations
01 Dec 2018
TL;DR: A simple and quick survey on the distributed deep learning system from algorithm perspective, distributed system perspective and applications perspective, and brings analysis on the restricts and prospects of the distributed methods.
Abstract: Deep learning have been widely used in various fields and has worked very well as a major role. While the gradual penetration into various fields, data quantity of each applications is increasing tremendously, and so as the computation complexity and model parameters. As an obvious result, the training and inference is time consuming. For example, a classic Resnet50 classification model will be trained in 14 days on a NVIDIA M40 GPU with ImageNet data set. Thus, distributed acceleration is a very useful way to dispatch the computation of training and even inference to scale of nodes in parallel and accelerate the whole process. Facebook's work and UC Berkeley's acceleration can training the Resnet-50 model within hour and minutes by distributed deep learning algorithm and system, representatively. As other distributed accelerations, it gives a possibility to accelerate large models on large data sets from weeks to minutes, which gives researchers and developers more space to explore and search. However, besides acceleration, what other issues will be confronted of the distributed deep learning system? Where is the upper limit of acceleration? What application will acceleration be used for? What is the price and cost of acceleration? In this paper, we will take a simple and quick survey on the distributed deep learning system from algorithm perspective, distributed system perspective and applications perspective. We will present several recent excellent works, and bring analysis on the restricts and prospects of the distributed methods.
21 citations
Cites background from "Neural Architecture Search with Rei..."
...Paper[26] [27] search network with fully trained and verified...
[...]
TL;DR: In this article, the authors proposed Auto-Ensemble (AE) to collect checkpoints of deep learning model and ensemble them automatically by adaptive learning rate scheduling algorithm, which can make the model converge to various local optima by scheduling the learning rate in once training.
Abstract: Ensembling deep learning models is a shortcut to promote its implementation in new scenarios, which can avoid tuning neural networks, losses and training algorithms from scratch. However, it is difficult to collect sufficient accurate and diverse models through once training. This paper proposes Auto-Ensemble (AE) to collect checkpoints of deep learning model and ensemble them automatically by adaptive learning rate scheduling algorithm. The advantage of this method is to make the model converge to various local optima by scheduling the learning rate in once training. When the number of local optimal solutions tends to be saturated, all the collected checkpoints are used for ensemble. Our method is universal, it can be applied to various scenarios. Experiment results on multiple datasets and neural networks demonstrate it is effective and competitive, especially on few-shot learning. Besides, we proposed a method to measure the distance among models. Then we can ensure the accuracy and diversity of collected models.
21 citations
01 Jun 2019
TL;DR: A Grid Search Network (GSN) for learning feature embeddings for fashion retrieval significantly outperforms existing state-of-art methods on benchmark fashion datasets and extends the reinforcement learning based strategy to learn custom kernel functions for SVM based classification over FashionMNIST and MNIST datasets, showing improved performance.
Abstract: Visual content based product retrieval has become increasingly important for e-commerce. Fashion retrieval, in particular, is a challenging problem owing to a wide range of deformations of clothing items along with visual distortions in their product images. In this paper, we propose a Grid Search Network (GSN) for learning feature embeddings for fashion retrieval. The proposed approach posits the training procedure as a search problem, focused on locating matches for a reference query image in a grid containing both positive and negative images w.r.t the query. The proposed framework significantly outperforms existing state-of-art methods on benchmark fashion datasets. We also utilize a reinforcement learning based strategy to learn a specialized transformation function which further improves retrieval performance when applied over the feature embeddings. We also extend the reinforcement learning based strategy to learn custom kernel functions for SVM based classification over FashionMNIST and MNIST datasets, showing improved performance. We highlight the generalization capabilities of this search strategy by showing performance improvement in search and attribution tasks in domains beyond fashion.
21 citations
Cites methods from "Neural Architecture Search with Rei..."
...Deep reinforcement learning based search mechanisms have been recently used for discovering neural optimization methods [1], neural activation functions [14] and neural architecture designs [26]....
[...]
...To this end, we use deep reinforcement learning based search mechanisms that have recently been used for discovering neural optimization methods [1], neural activation functions [14] and neural architecture designs [26]....
[...]
...For example, [26] uses a recurrent neural 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....
[...]
...As discussed, we built upon the existing reinforcement learning based search mechanisms [1, 14, 26]....
[...]
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)....
[...]