Paper Group ANR 107
Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning. A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model. Parsimonious Random Vector Functional Link Network for Data Streams. Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation. Proceedin …
Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning
| Title | Classification of Medical Images and Illustrations in the Biomedical Literature Using Synergic Deep Learning |
| Authors | Jianpeng Zhang, Yong Xia, Qi Wu, Yutong Xie |
| Abstract | The Classification of medical images and illustrations in the literature aims to label a medical image according to the modality it was produced or label an illustration according to its production attributes. It is an essential and challenging research hotspot in the area of automated literature review, retrieval and mining. The significant intra-class variation and inter-class similarity caused by the diverse imaging modalities and various illustration types brings a great deal of difficulties to the problem. In this paper, we propose a synergic deep learning (SDL) model to address this issue. Specifically, a dual deep convolutional neural network with a synergic signal system is designed to mutually learn image representation. The synergic signal is used to verify whether the input image pair belongs to the same category and to give the corrective feedback if a synergic error exists. Our SDL model can be trained ‘end to end’. In the test phase, the class label of an input can be predicted by averaging the likelihood probabilities obtained by two convolutional neural network components. Experimental results on the ImageCLEF2016 Subfigure Classification Challenge suggest that our proposed SDL model achieves the state-of-the art performance in this medical image classification problem and its accuracy is higher than that of the first place solution on the Challenge leader board so far. |
| Tasks | Image Classification |
| Published | 2017-06-28 |
| URL | http://arxiv.org/abs/1706.09092v1 |
| http://arxiv.org/pdf/1706.09092v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-medical-images-and |
| Repo | |
| Framework | |
A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model
| Title | A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model |
| Authors | Xi Chen, Yuanzhi Li, Jieming Mao |
| Abstract | We study the active learning problem of top-$k$ ranking from multi-wise comparisons under the popular multinomial logit model. Our goal is to identify the top-$k$ items with high probability by adaptively querying sets for comparisons and observing the noisy output of the most preferred item from each comparison. To achieve this goal, we design a new active ranking algorithm without using any information about the underlying items’ preference scores. We also establish a matching lower bound on the sample complexity even when the set of preference scores is given to the algorithm. These two results together show that the proposed algorithm is nearly instance optimal (similar to instance optimal [FLN03], but up to polylog factors). Our work extends the existing literature on rank aggregation in three directions. First, instead of studying a static problem with fixed data, we investigate the top-$k$ ranking problem in an active learning setting. Second, we show our algorithm is nearly instance optimal, which is a much stronger theoretical guarantee. Finally, we extend the pairwise comparison to the multi-wise comparison, which has not been fully explored in ranking literature. |
| Tasks | Active Learning |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.08238v2 |
| http://arxiv.org/pdf/1707.08238v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-nearly-instance-optimal-algorithm-for-top-k |
| Repo | |
| Framework | |
Parsimonious Random Vector Functional Link Network for Data Streams
| Title | Parsimonious Random Vector Functional Link Network for Data Streams |
| Authors | Mahardhika Pratama, Plamen P. Angelov, Edwin Lughofer |
| Abstract | The theory of random vector functional link network (RVFLN) has provided a breakthrough in the design of neural networks (NNs) since it conveys solid theoretical justification of randomized learning. Existing works in RVFLN are hardly scalable for data stream analytics because they are inherent to the issue of complexity as a result of the absence of structural learning scenarios. A novel class of RVLFN, namely parsimonious random vector functional link network (pRVFLN), is proposed in this paper. pRVFLN features an open structure paradigm where its network structure can be built from scratch and can be automatically generated in accordance with degree of nonlinearity and time-varying property of system being modelled. pRVFLN is equipped with complexity reduction scenarios where inconsequential hidden nodes can be pruned and input features can be dynamically selected. pRVFLN puts into perspective an online active learning mechanism which expedites the training process and relieves operator labelling efforts. In addition, pRVFLN introduces a non-parametric type of hidden node, developed using an interval-valued data cloud. The hidden node completely reflects the real data distribution and is not constrained by a specific shape of the cluster. All learning procedures of pRVFLN follow a strictly single-pass learning mode, which is applicable for an online real-time deployment. The efficacy of pRVFLN was rigorously validated through numerous simulations and comparisons with state-of-the art algorithms where it produced the most encouraging numerical results. Furthermore, the robustness of pRVFLN was investigated and a new conclusion is made to the scope of random parameters where it plays vital role to the success of randomized learning. |
| Tasks | Active Learning |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.02789v2 |
| http://arxiv.org/pdf/1704.02789v2.pdf | |
| PWC | https://paperswithcode.com/paper/parsimonious-random-vector-functional-link |
| Repo | |
| Framework | |
Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation
| Title | Taste or Addiction?: Using Play Logs to Infer Song Selection Motivation |
| Authors | Kosetsu Tsukuda, Masataka Goto |
| Abstract | Online music services are increasing in popularity. They enable us to analyze people’s music listening behavior based on play logs. Although it is known that people listen to music based on topic (e.g., rock or jazz), we assume that when a user is addicted to an artist, s/he chooses the artist’s songs regardless of topic. Based on this assumption, in this paper, we propose a probabilistic model to analyze people’s music listening behavior. Our main contributions are three-fold. First, to the best of our knowledge, this is the first study modeling music listening behavior by taking into account the influence of addiction to artists. Second, by using real-world datasets of play logs, we showed the effectiveness of our proposed model. Third, we carried out qualitative experiments and showed that taking addiction into account enables us to analyze music listening behavior from a new viewpoint in terms of how people listen to music according to the time of day, how an artist’s songs are listened to by people, etc. We also discuss the possibility of applying the analysis results to applications such as artist similarity computation and song recommendation. |
| Tasks | |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09439v1 |
| http://arxiv.org/pdf/1705.09439v1.pdf | |
| PWC | https://paperswithcode.com/paper/taste-or-addiction-using-play-logs-to-infer |
| Repo | |
| Framework | |
Proceedings Sixteenth Conference on Theoretical Aspects of Rationality and Knowledge
| Title | Proceedings Sixteenth Conference on Theoretical Aspects of Rationality and Knowledge |
| Authors | Jérôme Lang |
| Abstract | This volume consists of papers presented at the Sixteenth Conference on Theoretical Aspects of Rationality and Knowledge (TARK) held at the University of Liverpool, UK, from July 24 to 26, 2017. TARK conferences bring together researchers from a wide variety of fields, including Computer Science (especially, Artificial Intelligence, Cryptography, Distributed Computing), Economics (especially, Decision Theory, Game Theory, Social Choice Theory), Linguistics, Philosophy (especially, Philosophical Logic), and Cognitive Psychology, in order to further understand the issues involving reasoning about rationality and knowledge. |
| Tasks | |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.08250v1 |
| http://arxiv.org/pdf/1707.08250v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-sixteenth-conference-on |
| Repo | |
| Framework | |
A Dual-Source Approach for 3D Human Pose Estimation from a Single Image
| Title | A Dual-Source Approach for 3D Human Pose Estimation from a Single Image |
| Authors | Umar Iqbal, Andreas Doering, Hashim Yasin, Björn Krüger, Andreas Weber, Juergen Gall |
| Abstract | In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images. One major challenge for such methods, however, is the collection of training data. Specifically, collecting large amounts of training data containing unconstrained images annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of accurate 3D motion capture data, and the second source consists of unconstrained images with annotated 2D poses. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient 3D pose retrieval. To this end, we first convert the motion capture data into a normalized 2D pose space, and separately learn a 2D pose estimation model from the image data. During inference, we estimate the 2D pose and efficiently retrieve the nearest 3D poses. We then jointly estimate a mapping from the 3D pose space to the image and reconstruct the 3D pose. We provide a comprehensive evaluation of the proposed method and experimentally demonstrate the effectiveness of our approach, even when the skeleton structures of the two sources differ substantially. |
| Tasks | 3D Human Pose Estimation, Motion Capture, Pose Estimation |
| Published | 2017-05-08 |
| URL | http://arxiv.org/abs/1705.02883v2 |
| http://arxiv.org/pdf/1705.02883v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-dual-source-approach-for-3d-human-pose |
| Repo | |
| Framework | |
Distantly Supervised Road Segmentation
| Title | Distantly Supervised Road Segmentation |
| Authors | Satoshi Tsutsui, Tommi Kerola, Shunta Saito |
| Abstract | We present an approach for road segmentation that only requires image-level annotations at training time. We leverage distant supervision, which allows us to train our model using images that are different from the target domain. Using large publicly available image databases as distant supervisors, we develop a simple method to automatically generate weak pixel-wise road masks. These are used to iteratively train a fully convolutional neural network, which produces our final segmentation model. We evaluate our method on the Cityscapes dataset, where we compare it with a fully supervised approach. Further, we discuss the trade-off between annotation cost and performance. Overall, our distantly supervised approach achieves 93.8% of the performance of the fully supervised approach, while using orders of magnitude less annotation work. |
| Tasks | |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06118v1 |
| http://arxiv.org/pdf/1708.06118v1.pdf | |
| PWC | https://paperswithcode.com/paper/distantly-supervised-road-segmentation |
| Repo | |
| Framework | |
Active Learning for Structured Prediction from Partially Labeled Data
| Title | Active Learning for Structured Prediction from Partially Labeled Data |
| Authors | Mehran Khodabandeh, Zhiwei Deng, Mostafa S. Ibrahim, Shinichi Satoh, Greg Mori |
| Abstract | We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training set, then iterates querying a user for labels on unlabeled data and retraining the model. We propose a novel algorithm for selecting data for labeling, choosing examples to maximize expected information gain based on belief propagation inference. This is a general purpose method and can be applied to a variety of tasks or models. As a specific example we demonstrate this framework for learning to recognize human actions and group activities in video sequences. Experiments show that our proposed algorithm outperforms previous active learning methods and can achieve accuracy comparable to fully supervised methods while utilizing significantly less labeled data. |
| Tasks | Active Learning, Structured Prediction |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02342v2 |
| http://arxiv.org/pdf/1706.02342v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-for-structured-prediction |
| Repo | |
| Framework | |
Visual Servoing from Deep Neural Networks
| Title | Visual Servoing from Deep Neural Networks |
| Authors | Quentin Bateux, Eric Marchand, Jürgen Leitner, Francois Chaumette, Peter Corke |
| Abstract | We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF visual servoing. The paper describes how to create a dataset simulating various perturbations (occlusions and lighting conditions) from a single real-world image of the scene. A convolutional neural network is fine-tuned using this dataset to estimate the relative pose between two images of the same scene. The output of the network is then employed in a visual servoing control scheme. The method converges robustly even in difficult real-world settings with strong lighting variations and occlusions.A positioning error of less than one millimeter is obtained in experiments with a 6 DOF robot. |
| Tasks | |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08940v2 |
| http://arxiv.org/pdf/1705.08940v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-servoing-from-deep-neural-networks |
| Repo | |
| Framework | |
Navigability with Imperfect Information
| Title | Navigability with Imperfect Information |
| Authors | Kaya Deuser, Pavel Naumov |
| Abstract | The article studies navigability of an autonomous agent in a maze where some rooms may be indistinguishable. In a previous work the authors have shown that the properties of navigability in such a setting depend on whether an agent has perfect recall. Navigability by an agent with perfect recall is a transitive relation and without is not transitive. This article introduces a notion of restricted navigability and shows that a certain form of transitivity holds for restricted navigability, even for an agent without perfect recall. The main technical result is a sound and complete logical system describing the properties of restricted navigability. |
| Tasks | |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08255v1 |
| http://arxiv.org/pdf/1707.08255v1.pdf | |
| PWC | https://paperswithcode.com/paper/navigability-with-imperfect-information |
| Repo | |
| Framework | |
Random gradient extrapolation for distributed and stochastic optimization
| Title | Random gradient extrapolation for distributed and stochastic optimization |
| Authors | Guanghui Lan, Yi Zhou |
| Abstract | In this paper, we consider a class of finite-sum convex optimization problems defined over a distributed multiagent network with $m$ agents connected to a central server. In particular, the objective function consists of the average of $m$ ($\ge 1$) smooth components associated with each network agent together with a strongly convex term. Our major contribution is to develop a new randomized incremental gradient algorithm, namely random gradient extrapolation method (RGEM), which does not require any exact gradient evaluation even for the initial point, but can achieve the optimal ${\cal O}(\log(1/\epsilon))$ complexity bound in terms of the total number of gradient evaluations of component functions to solve the finite-sum problems. Furthermore, we demonstrate that for stochastic finite-sum optimization problems, RGEM maintains the optimal ${\cal O}(1/\epsilon)$ complexity (up to a certain logarithmic factor) in terms of the number of stochastic gradient computations, but attains an ${\cal O}(\log(1/\epsilon))$ complexity in terms of communication rounds (each round involves only one agent). It is worth noting that the former bound is independent of the number of agents $m$, while the latter one only linearly depends on $m$ or even $\sqrt m$ for ill-conditioned problems. To the best of our knowledge, this is the first time that these complexity bounds have been obtained for distributed and stochastic optimization problems. Moreover, our algorithms were developed based on a novel dual perspective of Nesterov’s accelerated gradient method. |
| Tasks | Stochastic Optimization |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05762v1 |
| http://arxiv.org/pdf/1711.05762v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-gradient-extrapolation-for-distributed |
| Repo | |
| Framework | |
QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds
| Title | QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds |
| Authors | Igor Halperin |
| Abstract | This paper presents a discrete-time option pricing model that is rooted in Reinforcement Learning (RL), and more specifically in the famous Q-Learning method of RL. We construct a risk-adjusted Markov Decision Process for a discrete-time version of the classical Black-Scholes-Merton (BSM) model, where the option price is an optimal Q-function, while the optimal hedge is a second argument of this optimal Q-function, so that both the price and hedge are parts of the same formula. Pricing is done by learning to dynamically optimize risk-adjusted returns for an option replicating portfolio, as in the Markowitz portfolio theory. Using Q-Learning and related methods, once created in a parametric setting, the model is able to go model-free and learn to price and hedge an option directly from data, and without an explicit model of the world. This suggests that RL may provide efficient data-driven and model-free methods for optimal pricing and hedging of options, once we depart from the academic continuous-time limit, and vice versa, option pricing methods developed in Mathematical Finance may be viewed as special cases of model-based Reinforcement Learning. Further, due to simplicity and tractability of our model which only needs basic linear algebra (plus Monte Carlo simulation, if we work with synthetic data), and its close relation to the original BSM model, we suggest that our model could be used for benchmarking of different RL algorithms for financial trading applications |
| Tasks | Q-Learning |
| Published | 2017-12-13 |
| URL | https://arxiv.org/abs/1712.04609v3 |
| https://arxiv.org/pdf/1712.04609v3.pdf | |
| PWC | https://paperswithcode.com/paper/qlbs-q-learner-in-the-black-scholes-merton |
| Repo | |
| Framework | |
A Study on Modeling of Inputting Electrical Power of Ultra High Power Electric Furnace by using Fuzzy Rule and Regression Model
| Title | A Study on Modeling of Inputting Electrical Power of Ultra High Power Electric Furnace by using Fuzzy Rule and Regression Model |
| Authors | Choe Un-Chol, Yun Kum-Il, Kwak Son-Il |
| Abstract | : In this paper a method to make inputting electrical model upon factors that affect melting process of high ultra power(UHP) electric furnace by using fuzzy rule and regression model is suggested and its effectiveness is verified with simulation experiment. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08512v1 |
| http://arxiv.org/pdf/1711.08512v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-on-modeling-of-inputting-electrical |
| Repo | |
| Framework | |
Evaluation of Classical Features and Classifiers in Brain-Computer Interface Tasks
| Title | Evaluation of Classical Features and Classifiers in Brain-Computer Interface Tasks |
| Authors | Ehsan Arbabi, Mohammad Bagher Shamsollahi |
| Abstract | Brain-Computer Interface (BCI) uses brain signals in order to provide a new method for communication between human and outside world. Feature extraction, selection and classification are among the main matters of concerns in signal processing stage of BCI. In this article, we present our findings about the most effective features and classifiers in some brain tasks. Six different groups of classical features and twelve classifiers have been examined in nine datasets of brain signal. The results indicate that energy of brain signals in {\alpha} and \b{eta} frequency bands, together with some statistical parameters are more effective, comparing to the other types of extracted features. In addition, Bayesian classifier with Gaussian distribution assumption and also Support Vector Machine (SVM) show to classify different BCI datasets more accurately than the other classifiers. We believe that the results can give an insight about a strategy for blind classification of brain signals in brain-computer interface. |
| Tasks | |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03252v2 |
| http://arxiv.org/pdf/1709.03252v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-classical-features-and |
| Repo | |
| Framework | |
An Ensemble Boosting Model for Predicting Transfer to the Pediatric Intensive Care Unit
| Title | An Ensemble Boosting Model for Predicting Transfer to the Pediatric Intensive Care Unit |
| Authors | Jonathan Rubin, Cristhian Potes, Minnan Xu-Wilson, Junzi Dong, Asif Rahman, Hiep Nguyen, David Moromisato |
| Abstract | Our work focuses on the problem of predicting the transfer of pediatric patients from the general ward of a hospital to the pediatric intensive care unit. Using data collected over 5.5 years from the electronic health records of two medical facilities, we develop classifiers based on adaptive boosting and gradient tree boosting. We further combine these learned classifiers into an ensemble model and compare its performance to a modified pediatric early warning score (PEWS) baseline that relies on expert defined guidelines. To gauge model generalizability, we perform an inter-facility evaluation where we train our algorithm on data from one facility and perform evaluation on a hidden test dataset from a separate facility. We show that improvements are witnessed over the PEWS baseline in accuracy (0.77 vs. 0.69), sensitivity (0.80 vs. 0.68), specificity (0.74 vs. 0.70) and AUROC (0.85 vs. 0.73). |
| Tasks | |
| Published | 2017-07-16 |
| URL | http://arxiv.org/abs/1707.04958v1 |
| http://arxiv.org/pdf/1707.04958v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-ensemble-boosting-model-for-predicting |
| Repo | |
| Framework | |
