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
04 Jun 2018
TL;DR: This thesis proposes a hierarchical framework based on sparse polynomial regression to predict the serving power, runtime, and energy consumption of deep learning applications, including convolutional neural networks.
Abstract: Energy and power are the main design constraints for modern high-performance computing systems. Indeed, energy eefficiency plays a critical role in performance improvement or energy saving for either state-of-the-art general purpose hardware platforms, such as FinFET-basedmulti-core systems, or widely-adopted applications such as deep learning applications and in particular, convolutional neural networks. To achieve higher energy eefficiency, power and performance models are key in enabling various predictive management algorithms or optimization techniques. To have accurate models, one needs to consider not only technology-related eff ects, including process variation, temperature eff ect inversion, and aging, but also application-related eff ects, such as the interaction between applications with software and hardware layers.In this thesis, we study these e ects and propose to combine machine learning techniques and domain knowledge to learn the performance, power, and energy models forhigh-performance computing systems. For technology-aware multi-core system design, we learn accurate performance and power models for FinFET-based multi-core systems considering various technology e ects. By applying these models, we propose efficient power-/performance-related management algorithms for multi-core systems to 1) increase performance under iso-power constraints; 2) reduce power while keeping the same performance; and 3) decrease aging eff ects with negligible power overhead for the same performance. Forapplication-aware computing system design, we propose a hierarchical framework based on sparse polynomial regression to predict the serving power, runtime, and energy consumption of deep learning applications, including convolutional neural networks. Extensive experimental results con rm the effectiveness of our proposed models, algorithms, and framework.
1 citations
Cites background from "Neural Architecture Search with Rei..."
...Such results are critical in many automatic neural architecture search algorithms [94]; 3) Typical CNNs are inconvenient or infeasible to profile if the service platform is different than the training platform....
[...]
Posted Content•
TL;DR: Zhang et al. as mentioned in this paper proposed a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects, which leads to the RGB feature enhancement and background distraction reduction by capturing the depth geometry prior.
Abstract: RGB-D salient object detection (SOD) is usually formulated as a problem of classification or regression over two modalities, i.e., RGB and depth. Hence, effective RGBD feature modeling and multi-modal feature fusion both play a vital role in RGB-D SOD. In this paper, we propose a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects. In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry prior. Moreover, to perform effective multi-modal feature fusion, we further present an automatic architecture search approach for RGB-D SOD, which does well in finding out a feasible architecture from our specially designed multi-modal multi-scale search space. Extensive experiments on seven standard benchmarks demonstrate the effectiveness of the proposed approach against the state-of-the-art.
1 citations
Posted Content•
25 Sep 2019
TL;DR: This work is one of the first attempts to propose a rigorous approach to training structured neural network architectures for RL problems that are of interest especially in mobile robotics with limited storage and computational resources.
Abstract: We present a new algorithm for finding compact neural networks encoding
reinforcement learning (RL) policies. To do it, we leverage in the novel RL
setting the theory of pointer networks and ENAS-type algorithms for
combinatorial optimization of RL policies as well as recent evolution
strategies (ES) optimization methods, and propose to define the combinatorial
search space to be the the set of different edge-partitionings (colorings) into
same-weight classes. For several RL tasks, we manage to learn colorings
translating to effective policies parameterized by as few as 17 weight
parameters, providing 6x compression over state-of-the-art compact policies
based on Toeplitz matrices. We believe that our work is one of the first
attempts to propose a rigorous approach to training structured neural network
architectures for RL problems that are of interest especially in mobile
robotics with limited storage and computational resources.
1 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...To do it, we leverage in the novel RL setting the theory of pointer networks and ENAS-type algorithms for combinatorial optimization of RL policies [1, 2, 3] as well as recent evolution strategies (ES) optimization methods [4] and propose to define the combinatorial search space to be the the set of different edge-partitionings (colorings) into same-weight classes....
[...]
...Interest in NAS algorithms started to grow rapidly when it was shown that they can design state-of-the-art architectures for image recognition and language modeling [3]....
[...]
...We leverage recent advances in the ENAS (Efficient Neural Architecture Search) literature and theory of pointer networks [1, 2, 3] to optimize over the combinatorial component of this objective and state of the art evolution strategies (ES) methods [4, 6, 7] to optimize over the RL objective....
[...]
Posted Content•
TL;DR: Li et al. as discussed by the authors proposed a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks.
Abstract: We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while the latency is almost constant. With these improvements, the accuracy of PP-LCNet can greatly surpass the previous network structure with the same inference time for classification. As shown in Figure 1, it outperforms the most state-of-the-art models. And for downstream tasks of computer vision, it also performs very well, such as object detection, semantic segmentation, etc. All our experiments are implemented based on PaddlePaddle. Code and pretrained models are available at PaddleClas.
1 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)....
[...]