Paper Group ANR 483
Bag of Recurrence Patterns Representation for Time-Series Classification. Abnormality Detection in Mammography using Deep Convolutional Neural Networks. Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification. The Case for Full-Matrix Adaptive Regularization. Personalized Education at Scale. Impact of Batch Size o …
Bag of Recurrence Patterns Representation for Time-Series Classification
| Title | Bag of Recurrence Patterns Representation for Time-Series Classification |
| Authors | Nima Hatami, Yann Gavet, Johan Debayle |
| Abstract | Time-Series Classification (TSC) has attracted a lot of attention in pattern recognition, because wide range of applications from different domains such as finance and health informatics deal with time-series signals. Bag of Features (BoF) model has achieved a great success in TSC task by summarizing signals according to the frequencies of “feature words” of a data-learned dictionary. This paper proposes embedding the Recurrence Plots (RP), a visualization technique for analysis of dynamic systems, in the BoF model for TSC. While the traditional BoF approach extracts features from 1D signal segments, this paper uses the RP to transform time-series into 2D texture images and then applies the BoF on them. Image representation of time-series enables us to explore different visual descriptors that are not available for 1D signals and to treats TSC task as a texture recognition problem. Experimental results on the UCI time-series classification archive demonstrates a significant accuracy boost by the proposed Bag of Recurrence patterns (BoR), compared not only to the existing BoF models, but also to the state-of-the art algorithms. |
| Tasks | Time Series, Time Series Classification |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.11111v1 |
| http://arxiv.org/pdf/1803.11111v1.pdf | |
| PWC | https://paperswithcode.com/paper/bag-of-recurrence-patterns-representation-for |
| Repo | |
| Framework | |
Abnormality Detection in Mammography using Deep Convolutional Neural Networks
| Title | Abnormality Detection in Mammography using Deep Convolutional Neural Networks |
| Authors | Pengcheng Xi, Chang Shu, Rafik Goubran |
| Abstract | Breast cancer is the most common cancer in women worldwide. The most common screening technology is mammography. To reduce the cost and workload of radiologists, we propose a computer aided detection approach for classifying and localizing calcifications and masses in mammogram images. To improve on conventional approaches, we apply deep convolutional neural networks (CNN) for automatic feature learning and classifier building. In computer-aided mammography, deep CNN classifiers cannot be trained directly on full mammogram images because of the loss of image details from resizing at input layers. Instead, our classifiers are trained on labelled image patches and then adapted to work on full mammogram images for localizing the abnormalities. State-of-the-art deep convolutional neural networks are compared on their performance of classifying the abnormalities. Experimental results indicate that VGGNet receives the best overall accuracy at 92.53% in classifications. For localizing abnormalities, ResNet is selected for computing class activation maps because it is ready to be deployed without structural change or further training. Our approach demonstrates that deep convolutional neural network classifiers have remarkable localization capabilities despite no supervision on the location of abnormalities is provided. |
| Tasks | Anomaly Detection |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01906v1 |
| http://arxiv.org/pdf/1803.01906v1.pdf | |
| PWC | https://paperswithcode.com/paper/abnormality-detection-in-mammography-using |
| Repo | |
| Framework | |
Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification
| Title | Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification |
| Authors | Yue Geng, Xinyu Luo |
| Abstract | Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for temporal deep learning classifiers due to the equal treatments of majority and minority class. Until recently, there were few works applying deep learning on imbalanced time-series classification (ITSC) tasks. Here, this paper aimed at tackling ITSC problems with deep learning. An adaptive cost-sensitive learning strategy was proposed to modify temporal deep learning models. Through the proposed strategy, classifiers could automatically assign misclassification penalties to each class. In the experimental section, the proposed method was utilized to modify five neural networks. They were evaluated on a large volume, real-life and imbalanced time-series dataset with six metrics. Each single network was also tested alone and combined with several mainstream data samplers. Experimental results illustrated that the proposed cost-sensitive modified networks worked well on ITSC tasks. Compared to other methods, the cost-sensitive convolution neural network and residual network won out in the terms of all metrics. Consequently, the proposed cost-sensitive learning strategy can be used to modify deep learning classifiers from cost-insensitive to cost-sensitive. Those cost-sensitive convolutional networks can be effectively applied to address ITSC issues. |
| Tasks | Time Series, Time Series Classification |
| Published | 2018-01-13 |
| URL | http://arxiv.org/abs/1801.04396v1 |
| http://arxiv.org/pdf/1801.04396v1.pdf | |
| PWC | https://paperswithcode.com/paper/cost-sensitive-convolution-based-neural |
| Repo | |
| Framework | |
The Case for Full-Matrix Adaptive Regularization
| Title | The Case for Full-Matrix Adaptive Regularization |
| Authors | Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang |
| Abstract | Adaptive regularization methods come in diagonal and full-matrix variants. However, only the former have enjoyed widespread adoption in training large-scale deep models. This is due to the computational overhead of manipulating a full matrix in high dimension. In this paper, we show how to make full-matrix adaptive regularization practical and useful. We present GGT, a truly scalable full-matrix adaptive optimizer. At the heart of our algorithm is an efficient method for computing the inverse square root of a low-rank matrix. We show that GGT converges to first-order local minima, providing the first rigorous theoretical analysis of adaptive regularization in non-convex optimization. In preliminary experiments, GGT trains faster across a variety of synthetic tasks and standard deep learning benchmarks. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.02958v1 |
| http://arxiv.org/pdf/1806.02958v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-case-for-full-matrix-adaptive |
| Repo | |
| Framework | |
Personalized Education at Scale
| Title | Personalized Education at Scale |
| Authors | Sam Saarinen, Evan Cater, Michael Littman |
| Abstract | Tailoring the presentation of information to the needs of individual students leads to massive gains in student outcomes~\cite{bloom19842}. This finding is likely due to the fact that different students learn differently, perhaps as a result of variation in ability, interest or other factors~\cite{schiefele1992interest}. Adapting presentations to the educational needs of an individual has traditionally been the domain of experts, making it expensive and logistically challenging to do at scale, and also leading to inequity in educational outcomes. Increased course sizes and large MOOC enrollments provide an unprecedented access to student data. We propose that emerging technologies in reinforcement learning (RL), as well as semi-supervised learning, natural language processing, and computer vision are critical to leveraging this data to provide personalized education at scale. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.10025v1 |
| http://arxiv.org/pdf/1809.10025v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-education-at-scale |
| Repo | |
| Framework | |
Impact of Batch Size on Stopping Active Learning for Text Classification
| Title | Impact of Batch Size on Stopping Active Learning for Text Classification |
| Authors | Garrett Beatty, Ethan Kochis, Michael Bloodgood |
| Abstract | When using active learning, smaller batch sizes are typically more efficient from a learning efficiency perspective. However, in practice due to speed and human annotator considerations, the use of larger batch sizes is necessary. While past work has shown that larger batch sizes decrease learning efficiency from a learning curve perspective, it remains an open question how batch size impacts methods for stopping active learning. We find that large batch sizes degrade the performance of a leading stopping method over and above the degradation that results from reduced learning efficiency. We analyze this degradation and find that it can be mitigated by changing the window size parameter of how many past iterations of learning are taken into account when making the stopping decision. We find that when using larger batch sizes, stopping methods are more effective when smaller window sizes are used. |
| Tasks | Active Learning, Text Classification |
| Published | 2018-01-24 |
| URL | http://arxiv.org/abs/1801.07887v2 |
| http://arxiv.org/pdf/1801.07887v2.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-batch-size-on-stopping-active |
| Repo | |
| Framework | |
Latent Agents in Networks: Estimation and Pricing
| Title | Latent Agents in Networks: Estimation and Pricing |
| Authors | Baris Ata, Alexandre Belloni, Ozan Candogan |
| Abstract | We focus on a setting where agents in a social network consume a product that exhibits positive local network externalities. A seller has access to data on past consumption decisions/prices for a subset of observable agents, and can target these agents with appropriate discounts to exploit network effects and increase her revenues. A novel feature of the model is that the observable agents potentially interact with additional latent agents. These latent agents can purchase the same product from a different channel, and are not observed by the seller. Observable agents influence each other both directly and indirectly through the influence they exert on the latent agents. The seller knows the connection structure of neither the observable nor the latent part of the network. Due to the presence of network externalities, an agent’s consumption decision depends not only on the price offered to her, but also on the consumption decisions of (and in turn the prices offered to) her neighbors in the underlying network. We investigate how the seller can use the available data to estimate the matrix that captures the dependence of observable agents’ consumption decisions on the prices offered to them. We provide an algorithm for estimating this matrix under an approximate sparsity condition, and obtain convergence rates for the proposed estimator despite the high dimensionality that allows more agents than observations. Importantly, we then show that this approximate sparsity condition holds under standard conditions present in the literature and hence our algorithms are applicable to a large class of networks. We establish that by using the estimated matrix the seller can construct prices that lead to a small revenue loss relative to revenue-maximizing prices under complete information, and the optimality gap vanishes relative to the size of the network. |
| Tasks | |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04878v2 |
| http://arxiv.org/pdf/1808.04878v2.pdf | |
| PWC | https://paperswithcode.com/paper/latent-agents-in-networks-estimation-and |
| Repo | |
| Framework | |
A Large-Scale Study of Language Models for Chord Prediction
| Title | A Large-Scale Study of Language Models for Chord Prediction |
| Authors | Filip Korzeniowski, David R. W. Sears, Gerhard Widmer |
| Abstract | We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of annotated chords known to us. This large amount of data allows us to systematically explore hyper-parameter settings for the recurrent neural networks—a crucial step in achieving good results with this model class. Our results show not only a quantitative difference between the models, but also a qualitative one: in contrast to static N-gram models, certain RNN configurations adapt to the songs at test time. This finding constitutes a further step towards the development of chord recognition systems that are more aware of local musical context than what was previously possible. |
| Tasks | Chord Recognition |
| Published | 2018-04-05 |
| URL | http://arxiv.org/abs/1804.01849v1 |
| http://arxiv.org/pdf/1804.01849v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-large-scale-study-of-language-models-for |
| Repo | |
| Framework | |
An efficient CNN for spectral reconstruction from RGB images
| Title | An efficient CNN for spectral reconstruction from RGB images |
| Authors | Yigit Baran Can, Radu Timofte |
| Abstract | Recently, the example-based single image spectral reconstruction from RGB images task, aka, spectral super-resolution was approached by means of deep learning by Galliani et al. The proposed very deep convolutional neural network (CNN) achieved superior performance on recent large benchmarks. However, Aeschbacher et al showed that comparable performance can be achieved by shallow learning method based on A+, a method introduced for image super-resolution by Timofte et al. In this paper, we propose a moderately deep CNN model and substantially improve the reported performance on three spectral reconstruction standard benchmarks: ICVL, CAVE, and NUS. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04647v1 |
| http://arxiv.org/pdf/1804.04647v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-cnn-for-spectral-reconstruction |
| Repo | |
| Framework | |
Articulatory Features for ASR of Pathological Speech
| Title | Articulatory Features for ASR of Pathological Speech |
| Authors | Emre Yılmaz, Vikramjit Mitra, Chris Bartels, Horacio Franco |
| Abstract | In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech. Despite long-lasting efforts to build speaker- and text-independent ASR systems for people with dysarthria, the performance of state-of-the-art systems is still considerably lower on this type of speech than on normal speech. The most prominent reason for the inferior performance is the high variability in pathological speech that is characterized by the spectrotemporal deviations caused by articulatory impairments due to various etiologies. To cope with this high variation, we propose to use speech representations which utilize articulatory information together with the acoustic properties. A designated acoustic model, namely a fused-feature-map convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time convolution on articulatory features is trained and tested on a Dutch and a Flemish pathological speech corpus. The ASR performance of fCNN-based ASR system using joint features is compared to other neural network architectures such conventional CNNs and time-frequency convolutional networks (TFCNNs) in several training scenarios. |
| Tasks | Speech Recognition |
| Published | 2018-07-28 |
| URL | http://arxiv.org/abs/1807.10948v1 |
| http://arxiv.org/pdf/1807.10948v1.pdf | |
| PWC | https://paperswithcode.com/paper/articulatory-features-for-asr-of-pathological |
| Repo | |
| Framework | |
Managing engineering systems with large state and action spaces through deep reinforcement learning
| Title | Managing engineering systems with large state and action spaces through deep reinforcement learning |
| Authors | C. P. Andriotis, K. G. Papakonstantinou |
| Abstract | Decision-making for engineering systems can be efficiently formulated as a Markov Decision Process (MDP) or a Partially Observable MDP (POMDP). Typical MDP and POMDP solution procedures utilize offline knowledge about the environment and provide detailed policies for relatively small systems with tractable state and action spaces. However, in large multi-component systems the sizes of these spaces easily explode, as system states and actions scale exponentially with the number of components, whereas environment dynamics are difficult to be described in explicit forms for the entire system and may only be accessible through numerical simulators. In this work, to address these issues, an integrated Deep Reinforcement Learning (DRL) framework is introduced. The Deep Centralized Multi-agent Actor Critic (DCMAC) is developed, an off-policy actor-critic DRL approach, providing efficient life-cycle policies for large multi-component systems operating in high-dimensional spaces. Apart from deep function approximations that parametrize large state spaces, DCMAC also adopts a factorized representation of the system actions, being able to designate individualized component- and subsystem-level decisions, while maintaining a centralized value function for the entire system. DCMAC compares well against Deep Q-Network (DQN) solutions and exact policies, where applicable, and outperforms optimized baselines that are based on time-based, condition-based and periodic policies. |
| Tasks | Decision Making |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.02052v1 |
| http://arxiv.org/pdf/1811.02052v1.pdf | |
| PWC | https://paperswithcode.com/paper/managing-engineering-systems-with-large-state |
| Repo | |
| Framework | |
Supervising Feature Influence
| Title | Supervising Feature Influence |
| Authors | Shayak Sen, Piotr Mardziel, Anupam Datta, Matthew Fredrikson |
| Abstract | Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier using datapoints that may be atypical of its training distribution. Standard methods for training classifiers that minimize empirical risk do not constrain the behavior of the classifier on such datapoints. As a result, training to minimize empirical risk does not distinguish among classifiers that agree on predictions in the training distribution but have wildly different causal influences. We term this problem covariate shift in causal testing and formally characterize conditions under which it arises. As a solution to this problem, we propose a novel active learning algorithm that constrains the influence measures of the trained model. We prove that any two predictors whose errors are close on both the original training distribution and the distribution of atypical points are guaranteed to have causal influences that are also close. Further, we empirically demonstrate with synthetic labelers that our algorithm trains models that (i) have similar causal influences as the labeler’s model, and (ii) generalize better to out-of-distribution points while (iii) retaining their accuracy on in-distribution points. |
| Tasks | Active Learning |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10815v2 |
| http://arxiv.org/pdf/1803.10815v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervising-feature-influence |
| Repo | |
| Framework | |
A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation
| Title | A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation |
| Authors | Clayton Scott |
| Abstract | In the problem of domain adaptation for binary classification, the learner is presented with labeled examples from a source domain, and must correctly classify unlabeled examples from a target domain, which may differ from the source. Previous work on this problem has assumed that the performance measure of interest is the expected value of some loss function. We introduce a new Neyman-Pearson-like criterion and argue that, for this optimality criterion, stronger domain adaptation results are possible than what has previously been established. In particular, we study a class of domain adaptation problems that generalizes both the covariate shift assumption and a model for feature-dependent label noise, and establish optimal classification on the target domain despite not having access to labelled data from this domain. |
| Tasks | Domain Adaptation |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01545v2 |
| http://arxiv.org/pdf/1810.01545v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-generalized-neyman-pearson-criterion-for |
| Repo | |
| Framework | |
Traffic Danger Recognition With Surveillance Cameras Without Training Data
| Title | Traffic Danger Recognition With Surveillance Cameras Without Training Data |
| Authors | Lijun Yu, Dawei Zhang, Xiangqun Chen, Alexander Hauptmann |
| Abstract | We propose a traffic danger recognition model that works with arbitrary traffic surveillance cameras to identify and predict car crashes. There are too many cameras to monitor manually. Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories. For normal traffic, it supports real-time proactive safety checks of speeds and distances between vehicles to provide insights about possible high-risk areas. We achieve good prediction and recognition of car crashes without using any labeled training data of crashes. Experiments on the BrnoCompSpeed dataset show that our model can accurately monitor the road, with mean errors of 1.80% for distance measurement, 2.77 km/h for speed measurement, 0.24 m for car position prediction, and 2.53 km/h for speed prediction. |
| Tasks | 3D Reconstruction |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.11969v1 |
| http://arxiv.org/pdf/1811.11969v1.pdf | |
| PWC | https://paperswithcode.com/paper/traffic-danger-recognition-with-surveillance |
| Repo | |
| Framework | |
Blind Predicting Similar Quality Map for Image Quality Assessment
| Title | Blind Predicting Similar Quality Map for Image Quality Assessment |
| Authors | Da Pan, Ping Shi, Ming Hou, Zefeng Ying, Sizhe Fu, Yuan Zhang |
| Abstract | A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner. In this paper, we propose a simple and efficient BIQA model based on a novel framework which consists of a fully convolutional neural network (FCNN) and a pooling network to solve this problem. In principle, FCNN is capable of predicting a pixel-by-pixel similar quality map only from a distorted image by using the intermediate similarity maps derived from conventional full-reference image quality assessment methods. The predicted pixel-by-pixel quality maps have good consistency with the distortion correlations between the reference and distorted images. Finally, a deep pooling network regresses the quality map into a score. Experiments have demonstrated that our predictions outperform many state-of-the-art BIQA methods. |
| Tasks | Blind Image Quality Assessment, Image Quality Assessment |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08493v2 |
| http://arxiv.org/pdf/1805.08493v2.pdf | |
| PWC | https://paperswithcode.com/paper/blind-predicting-similar-quality-map-for |
| Repo | |
| Framework | |
