July 29, 2019

2857 words 14 mins read

Paper Group AWR 165

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. Predicting readmission risk from doctors’ notes. GaKCo: a Fast GApped k-mer string Kernel using COunting. CARLA: An Open Urban Driving Simulator. Enhancing Person Re-identification in a Self-trained Subspace. Deep-Person: Learning Discriminative Deep Features fo …

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm


Title	Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Authors	David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis
Abstract	The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.
Tasks	Game of Chess, Game of Go, Game of Shogi
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01815v1
PDF	http://arxiv.org/pdf/1712.01815v1.pdf
PWC	https://paperswithcode.com/paper/mastering-chess-and-shogi-by-self-play-with-a
Repo	https://github.com/davidokao/beta-zero
Framework	none

Predicting readmission risk from doctors’ notes


Title	Predicting readmission risk from doctors’ notes
Authors	Erin Craig, Carlos Arias, David Gillman
Abstract	We develop a model using deep learning techniques and natural language processing on unstructured text from medical records to predict hospital-wide $30$-day unplanned readmission, with c-statistic $.70$. Our model is constructed to allow physicians to interpret the significant features for prediction.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10663v2
PDF	http://arxiv.org/pdf/1711.10663v2.pdf
PWC	https://paperswithcode.com/paper/predicting-readmission-risk-from-doctors
Repo	https://github.com/farinstitute/ReadmissionRiskDoctorNotes
Framework	none

GaKCo: a Fast GApped k-mer string Kernel using COunting


Title	GaKCo: a Fast GApped k-mer string Kernel using COunting
Authors	Ritambhara Singh, Arshdeep Sekhon, Kamran Kowsari, Jack Lanchantin, Beilun Wang, Yanjun Qi
Abstract	String Kernel (SK) techniques, especially those using gapped $k$-mers as features (gk), have obtained great success in classifying sequences like DNA, protein, and text. However, the state-of-the-art gk-SK runs extremely slow when we increase the dictionary size ($\Sigma$) or allow more mismatches ($M$). This is because current gk-SK uses a trie-based algorithm to calculate co-occurrence of mismatched substrings resulting in a time cost proportional to $O(\Sigma^{M})$. We propose a \textbf{fast} algorithm for calculating \underline{Ga}pped $k$-mer \underline{K}ernel using \underline{Co}unting (GaKCo). GaKCo uses associative arrays to calculate the co-occurrence of substrings using cumulative counting. This algorithm is fast, scalable to larger $\Sigma$ and $M$, and naturally parallelizable. We provide a rigorous asymptotic analysis that compares GaKCo with the state-of-the-art gk-SK. Theoretically, the time cost of GaKCo is independent of the $\Sigma^{M}$ term that slows down the trie-based approach. Experimentally, we observe that GaKCo achieves the same accuracy as the state-of-the-art and outperforms its speed by factors of 2, 100, and 4, on classifying sequences of DNA (5 datasets), protein (12 datasets), and character-based English text (2 datasets), respectively. GaKCo is shared as an open source tool at \url{https://github.com/QData/GaKCo-SVM}
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07468v3
PDF	http://arxiv.org/pdf/1704.07468v3.pdf
PWC	https://paperswithcode.com/paper/gakco-a-fast-gapped-k-mer-string-kernel-using
Repo	https://github.com/QData/GaKCo-SVM
Framework	tf

CARLA: An Open Urban Driving Simulator


Title	CARLA: An Open Urban Driving Simulator
Authors	Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun
Abstract	We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end-to-end model trained via reinforcement learning. The approaches are evaluated in controlled scenarios of increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform’s utility for autonomous driving research. The supplementary video can be viewed at https://youtu.be/Hp8Dz-Zek2E
Tasks	Autonomous Driving, Imitation Learning
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03938v1
PDF	http://arxiv.org/pdf/1711.03938v1.pdf
PWC	https://paperswithcode.com/paper/carla-an-open-urban-driving-simulator
Repo	https://github.com/filippogiruzzi/semantic_segmentation
Framework	tf

Enhancing Person Re-identification in a Self-trained Subspace


Title	Enhancing Person Re-identification in a Self-trained Subspace
Authors	Xun Yang, Meng Wang, Richang Hong, Qi Tian, Yong Rui
Abstract	Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms have been developed in the fully-supervised setting, requiring access to a large amount of labeled training data. However, the main bottleneck for fully-supervised re-ID is the limited availability of labeled training samples. To address this problem, in this paper, we propose a self-trained subspace learning paradigm for person re-ID which effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched. The proposed approach first constructs pseudo pairwise relationships among unlabeled persons using the k-nearest neighbors algorithm. Then, with the pseudo pairwise relationships, the unlabeled samples can be easily combined with the labeled samples to learn a discriminative projection by solving an eigenvalue problem. In addition, we refine the pseudo pairwise relationships iteratively, which further improves the learning performance. A multi-kernel embedding strategy is also incorporated into the proposed approach to cope with the non-linearity in person’s appearance and explore the complementation of multiple kernels. In this way, the performance of person re-ID can be greatly enhanced when training data are insufficient. Experimental results on six widely-used datasets demonstrate the effectiveness of our approach and its performance can be comparable to the reported results of most state-of-the-art fully-supervised methods while using much fewer labeled data.
Tasks	Person Re-Identification
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06020v2
PDF	http://arxiv.org/pdf/1704.06020v2.pdf
PWC	https://paperswithcode.com/paper/enhancing-person-re-identification-in-a-self
Repo	https://github.com/Xun-Yang/ReID_slef-training_TOMM2017
Framework	none

Deep-Person: Learning Discriminative Deep Features for Person Re-Identification


Title	Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
Authors	Xiang Bai, Mingkun Yang, Tengteng Huang, Zhiyong Dou, Rui Yu, Yongchao Xu
Abstract	Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor. However, the spatial context between these parts is ignored for the independent extractor to each separate part. In this paper, we propose to apply Long Short-Term Memory (LSTM) in an end-to-end way to model the pedestrian, seen as a sequence of body parts from head to foot. Integrating the contextual information strengthens the discriminative ability of local representation. We also leverage the complementary information between local and global feature. Furthermore, we integrate both identification task and ranking task in one network, where a discriminative embedding and a similarity measurement are learned concurrently. This results in a novel three-branch framework named Deep-Person, which learns highly discriminative features for person Re-ID. Experimental results demonstrate that Deep-Person outperforms the state-of-the-art methods by a large margin on three challenging datasets including Market-1501, CUHK03, and DukeMTMC-reID. Specifically, combining with a re-ranking approach, we achieve a 90.84% mAP on Market-1501 under single query setting.
Tasks	Person Re-Identification
Published	2017-11-29
URL	https://arxiv.org/abs/1711.10658v4
PDF	https://arxiv.org/pdf/1711.10658v4.pdf
PWC	https://paperswithcode.com/paper/deep-person-learning-discriminative-deep
Repo	https://github.com/zydou/Deep-Person
Framework	pytorch

Recurrent Neural Networks with Top-k Gains for Session-based Recommendations


Title	Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
Authors	Balázs Hidasi, Alexandros Karatzoglou
Abstract	RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. The use of RNNs provides impressive performance benefits over classical methods in session-based recommendations. In this work we introduce novel ranking loss functions tailored to RNNs in the recommendation setting. The improved performance of these losses over alternatives, along with further tricks and refinements described in this work, allow for an overall improvement of up to 35% in terms of MRR and Recall@20 over previous session-based RNN solutions and up to 53% over classical collaborative filtering approaches. Unlike data augmentation-based improvements, our method does not increase training times significantly. We further demonstrate the performance gain of the RNN over baselines in an online A/B test.
Tasks	Data Augmentation, Session-Based Recommendations
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03847v3
PDF	http://arxiv.org/pdf/1706.03847v3.pdf
PWC	https://paperswithcode.com/paper/recurrent-neural-networks-with-top-k-gains
Repo	https://github.com/bekleyis95/RNN-RecSys
Framework	none

Deep learning in remote sensing: a review


Title	Deep learning in remote sensing: a review
Authors	Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, Friedrich Fraundorfer
Abstract	Standing at the paradigm shift towards data-intensive science, machine learning techniques are becoming increasingly important. In particular, as a major breakthrough in the field, deep learning has proven as an extremely powerful tool in many fields. Shall we embrace deep learning as the key to all? Or, should we resist a ‘black-box’ solution? There are controversial opinions in the remote sensing community. In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with. More importantly, we advocate remote sensing scientists to bring their expertise into deep learning, and use it as an implicit general model to tackle unprecedented large-scale influential challenges, such as climate change and urbanization.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.03959v1
PDF	http://arxiv.org/pdf/1710.03959v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-remote-sensing-a-review
Repo	https://github.com/bluove/__DL-prediction-on-earth-phenology
Framework	tf

Bayesian Hybrid Matrix Factorisation for Data Integration


Title	Bayesian Hybrid Matrix Factorisation for Data Integration
Authors	Thomas Brouwer, Pietro Lió
Abstract	We introduce a novel Bayesian hybrid matrix factorisation model (HMF) for data integration, based on combining multiple matrix factorisation methods, that can be used for in- and out-of-matrix prediction of missing values. The model is very general and can be used to integrate many datasets across different entity types, including repeated experiments, similarity matrices, and very sparse datasets. We apply our method on two biological applications, and extensively compare it to state-of-the-art machine learning and matrix factorisation models. For in-matrix predictions on drug sensitivity datasets we obtain consistently better performances than existing methods. This is especially the case when we increase the sparsity of the datasets. Furthermore, we perform out-of-matrix predictions on methylation and gene expression datasets, and obtain the best results on two of the three datasets, especially when the predictivity of datasets is high.
Tasks
Published	2017-04-17
URL	http://arxiv.org/abs/1704.04962v1
PDF	http://arxiv.org/pdf/1704.04962v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-hybrid-matrix-factorisation-for-data
Repo	https://github.com/ThomasBrouwer/BNMTF_ARD
Framework	none


Title	Joint Pose and Principal Curvature Refinement Using Quadrics
Authors	Andrew Spek, Tom Drummond
Abstract	In this paper we present a novel joint approach for optimising surface curvature and pose alignment. We present two implementations of this joint optimisation strategy, including a fast implementation that uses two frames and an offline multi-frame approach. We demonstrate an order of magnitude improvement in simulation over state of the art dense relative point-to-plane Iterative Closest Point (ICP) pose alignment using our dense joint frame-to-frame approach and show comparable pose drift to dense point-to-plane ICP bundle adjustment using low-cost depth sensors. Additionally our improved joint quadric based approach can be used to more accurately estimate surface curvature on noisy point clouds than previous approaches.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00381v2
PDF	http://arxiv.org/pdf/1707.00381v2.pdf
PWC	https://paperswithcode.com/paper/joint-pose-and-principal-curvature-refinement
Repo	https://github.com/aspek1/QuadricCurvature
Framework	none

Comparative Study of Inference Methods for Bayesian Nonnegative Matrix Factorisation


Title	Comparative Study of Inference Methods for Bayesian Nonnegative Matrix Factorisation
Authors	Thomas Brouwer, Jes Frellsen, Pietro Lió
Abstract	In this paper, we study the trade-offs of different inference approaches for Bayesian matrix factorisation methods, which are commonly used for predicting missing values, and for finding patterns in the data. In particular, we consider Bayesian nonnegative variants of matrix factorisation and tri-factorisation, and compare non-probabilistic inference, Gibbs sampling, variational Bayesian inference, and a maximum-a-posteriori approach. The variational approach is new for the Bayesian nonnegative models. We compare their convergence, and robustness to noise and sparsity of the data, on both synthetic and real-world datasets. Furthermore, we extend the models with the Bayesian automatic relevance determination prior, allowing the models to perform automatic model selection, and demonstrate its efficiency.
Tasks	Bayesian Inference, Model Selection
Published	2017-07-13
URL	http://arxiv.org/abs/1707.05147v1
PDF	http://arxiv.org/pdf/1707.05147v1.pdf
PWC	https://paperswithcode.com/paper/comparative-study-of-inference-methods-for
Repo	https://github.com/ThomasBrouwer/BNMTF_ARD
Framework	none

Bayesian Sparsification of Recurrent Neural Networks


Title	Bayesian Sparsification of Recurrent Neural Networks
Authors	Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry Vetrov
Abstract	Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse Variational Dropout eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique to sparsify recurrent neural networks. To account for recurrent specifics we also rely on Binary Variational Dropout for RNN. We report 99.5% sparsity level on sentiment analysis task without a quality drop and up to 87% sparsity level on language modeling task with slight loss of accuracy.
Tasks	Language Modelling, Sentiment Analysis
Published	2017-07-31
URL	http://arxiv.org/abs/1708.00077v1
PDF	http://arxiv.org/pdf/1708.00077v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-sparsification-of-recurrent-neural
Repo	https://github.com/ars-ashuha/variational-dropout-sparsifies-dnn
Framework	tf

metboost: Exploratory regression analysis with hierarchically clustered data


Title	metboost: Exploratory regression analysis with hierarchically clustered data
Authors	Patrick J. Miller, Daniel B. McArtor, Gitta H. Lubke
Abstract	As data collections become larger, exploratory regression analysis becomes more important but more challenging. When observations are hierarchically clustered the problem is even more challenging because model selection with mixed effect models can produce misleading results when nonlinear effects are not included into the model (Bauer and Cai, 2009). A machine learning method called boosted decision trees (Friedman, 2001) is a good approach for exploratory regression analysis in real data sets because it can detect predictors with nonlinear and interaction effects while also accounting for missing data. We propose an extension to boosted decision decision trees called metboost for hierarchically clustered data. It works by constraining the structure of each tree to be the same across groups, but allowing the terminal node means to differ. This allows predictors and split points to lead to different predictions within each group, and approximates nonlinear group specific effects. Importantly, metboost remains computationally feasible for thousands of observations and hundreds of predictors that may contain missing values. We apply the method to predict math performance for 15,240 students from 751 schools in data collected in the Educational Longitudinal Study 2002 (Ingels et al., 2007), allowing 76 predictors to have unique effects for each school. When comparing results to boosted decision trees, metboost has 15% improved prediction performance. Results of a large simulation study show that metboost has up to 70% improved variable selection performance and up to 30% improved prediction performance compared to boosted decision trees when group sizes are small
Tasks	Model Selection
Published	2017-02-13
URL	http://arxiv.org/abs/1702.03994v1
PDF	http://arxiv.org/pdf/1702.03994v1.pdf
PWC	https://paperswithcode.com/paper/metboost-exploratory-regression-analysis-with
Repo	https://github.com/patr1ckm/mvtboost
Framework	none

Learning Chained Deep Features and Classifiers for Cascade in Object Detection


Title	Learning Chained Deep Features and Classifiers for Cascade in Object Detection
Authors	Wanli Ouyang, Ku Wang, Xin Zhu, Xiaogang Wang
Abstract	Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, the cascaded classifier at a stage is aided by the classification scores in previous stages. Feature chaining is further proposed so that the feature learning for the current cascade stage uses the features in previous stages as the prior information. The chained ConvNet features and classifiers of multiple stages are jointly learned in an end-to-end network. In this way, features and classifiers at latter stages handle more difficult samples with the help of features and classifiers in previous stages. It yields consistent boost in detection performance on benchmarks like PASCAL VOC 2007 and ImageNet. Combined with better region proposal, CC-Net leads to state-of-the-art result of 81.1% mAP on PASCAL VOC 2007.
Tasks	Object Detection
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07054v1
PDF	http://arxiv.org/pdf/1702.07054v1.pdf
PWC	https://paperswithcode.com/paper/learning-chained-deep-features-and
Repo	https://github.com/wk910930/ccnn
Framework	none

Quantum transport senses community structure in networks


Title	Quantum transport senses community structure in networks
Authors	Chenchao Zhao, Jun S. Song
Abstract	Quantum time evolution exhibits rich physics, attributable to the interplay between the density and phase of a wave function. However, unlike classical heat diffusion, the wave nature of quantum mechanics has not yet been extensively explored in modern data analysis. We propose that the Laplace transform of quantum transport (QT) can be used to construct an ensemble of maps from a given complex network to a circle $S^1$, such that closely-related nodes on the network are grouped into sharply concentrated clusters on $S^1$. The resulting QT clustering (QTC) algorithm is as powerful as the state-of-the-art spectral clustering in discerning complex geometric patterns and more robust when clusters show strong density variations or heterogeneity in size. The observed phenomenon of QTC can be interpreted as a collective behavior of the microscopic nodes that evolve as macroscopic cluster orbitals in an effective tight-binding model recapitulating the network. Python source code implementing the algorithm and examples are available at https://github.com/jssong-lab/QTC.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04979v2
PDF	http://arxiv.org/pdf/1711.04979v2.pdf
PWC	https://paperswithcode.com/paper/quantum-transport-senses-community-structure
Repo	https://github.com/jssong-lab/QTC
Framework	none