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
22 Sep 2020
TL;DR: It is demonstrated that network architecture and its coefficients can be learned together by unifying concepts of evolutionary search within a population based traditional training process.
Abstract: Neural Architecture Search (NAS), which automates the discovery of efficient neural networks, has demonstrated substantial potential in achieving state of the art performance in a variety of domains such as image classification and language understanding. In most NAS techniques, training of a neural network is considered a separate task or a performance estimation strategy to perform the architecture search. We demonstrate that network architecture and its coefficients can be learned together by unifying concepts of evolutionary search within a population based traditional training process. The consolidation is realised by cleaving the training process into pieces and then put back together in combination with evolution based architecture search operators. We show the competence and versatility of this concept by using datasets from two different domains, CIFAR-10 for image classification and PAMAP2 for human activity recognition. The search is constrained using minimum and maximum bounds on architecture parameters to restrict the size of neural network from becoming too large. Beginning the search from random untrained models, it achieves a fully trained model with a competent architecture, reaching an accuracy of 92.5% and 94.36% on CIFAR-10 and PAMAP2 respectively.
17 citations
Cites methods from "Neural Architecture Search with Rei..."
...RL method [37] trained over 10,000 of neural architectures, requiring thousands of GPU days and another very efficient evolutionary search [13] still takes 56 GPU days to converge....
[...]
...In RL methods [4,26,37], the reward of the RL agent is dependent on the validation performance of the trained architecture....
[...]
...Popular approaches for Neural Architecture Search (NAS) use reinforcement learning [26,37] and evolutionary algorithms [23,27]....
[...]
20 Sep 2020
TL;DR: In this article, a novel method combining evolutionary meta-learning and task-based selective backpropagation is proposed for computing task weights leading to reliable network training, which outperforms state-of-the-art methods by a significant margin on a two-task application.
Abstract: Deep multi-task networks are of particular interest for autonomous driving systems. They can potentially strike an excellent trade-off between predictive performance, hardware constraints and efficient use of information from multiple types of annotations and modalities. However, training such models is non-trivial and requires balancing learning over all tasks as their respective losses display different scales, ranges and dynamics across training. Multiple task weighting methods that adjust the losses in an adaptive way have been proposed recently on different datasets and combinations of tasks, making it difficult to compare them. In this work, we review and systematically evaluate nine task weighting strategies on common grounds on three automotive datasets (KITTI, Cityscapes and WoodScape). We then propose a novel method combining evolutionary meta-learning and task-based selective backpropagation, for computing task weights leading to reliable network training. Our method outperforms state-of-the-art methods by a significant margin on a two-task application.
17 citations
01 Sep 2020
TL;DR: The relationship between hardware platforms and the competency awareness of a neural network is examined, highlighting how hardware developments can impact uncertainty estimation quality, and exploring the innovations required in order to build competency-aware neural networks in resource constrained hardware platforms.
Abstract: The ability to estimate the uncertainty of predictions made by a neural network is essential when applying neural networks to tasks such as medical diagnosis and autonomous vehicles. The approach is of particular relevance when deploying the networks on devices with limited hardware resources, but existing competency-aware neural networks largely ignore any resource constraints. Here we examine the relationship between hardware platforms and the competency awareness of a neural network. We highlight the impact of two key areas of hardware development — increasing memory size of accelerator architectures and device-to-device variation in the emerging devices typically used in in-memory computing — on uncertainty estimation quality. We also consider the challenges that developments in uncertainty estimation methods impose on hardware designs. Finally, we explore the innovations required in terms of hardware, software, and hardware–software co-design in order to build future competency-aware neural networks. This Perspective examines the relationship between hardware platforms and the competency awareness of a neural network, highlighting how hardware developments can impact uncertainty estimation quality, and exploring the innovations required in order to build competency-aware neural networks in resource constrained hardware platforms.
17 citations
Proceedings Article•
01 Jan 2020TL;DR: This paper devise an Auto Learning Attention (AutoLA) method, which is the first attempt on automatic attention design, and defines a novel attention module named high order group attention (HOGA) as a directed acyclic graph (DAG) where each group represents a node, and each edge represents an operation of heterogeneous attentions.
Abstract: Attention modules have been demonstrated effective in strengthening the representation ability of a neural network via reweighting spatial or channel features or stacking both operations sequentially. However, designing the structures of different attention operations requires a bulk of computation and extensive expertise. In this paper, we devise an Auto Learning Attention (AutoLA) method, which is the first attempt on automatic attention design. Specifically, we define a novel attention module named high order group attention (HOGA) as a directed acyclic graph (DAG) where each group represents a node, and each edge represents an operation of heterogeneous attentions. A typical HOGA architecture can be searched automatically via the differential AutoLA method within 1 GPU day using the ResNet-20 backbone on CIFAR10. Further, the searched attention module can generalize to various backbones as a plug-and-play component and outperforms popular manually designed channel and spatial attentions for many vision tasks, including image classification on CIFAR100 and ImageNet, object detection and human keypoint detection on COCO dataset. Code is available at https://github.com/btma48/AutoLA.
17 citations
Additional excerpts
...In terms of the NAS methods, reinforcement learning [9, 21, 22], sequential optimization [10, 23], evolutionary algorithms [24, 25, 26], random search [27, 28], and performance predictors [29, 30] tend to demand immense computational resources which probably not suitable for efficient search....
[...]
...Recent years have witnessed the unprecedented success of neural architecture search (NAS) in the automated design of neural network architectures, surpassing human designs on various tasks [6, 7, 8, 9, 10, 11, 12]....
[...]
Posted Content•
TL;DR: In this article, the authors present Rapid Exploration of Model Architectures and Parameters, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures.
Abstract: Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configure a successful model. This means model builders often have to experiment with different configurations by manually programming different architectures (which is tedious and time consuming) or rely on purely automated approaches to generate and train the architectures (which is expensive). In this paper, we present Rapid Exploration of Model Architectures and Parameters, or REMAP, a visual analytics tool that allows a model builder to discover a deep learning model quickly via exploration and rapid experimentation of neural network architectures. In REMAP, the user explores the large and complex parameter space for neural network architectures using a combination of global inspection and local experimentation. Through a visual overview of a set of models, the user identifies interesting clusters of architectures. Based on their findings, the user can run ablation and variation experiments to identify the effects of adding, removing, or replacing layers in a given architecture and generate new models accordingly. They can also handcraft new models using a simple graphical interface. As a result, a model builder can build deep learning models quickly, efficiently, and without manual programming. We inform the design of REMAP through a design study with four deep learning model builders. Through a use case, we demonstrate that REMAP allows users to discover performant neural network architectures efficiently using visual exploration and user-defined semi-automated searches through the model space.
17 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)....
[...]