Paper Group ANR 478
Estimating and abstracting the 3D structure of bones using neural networks on X-ray (2D) images. Heterogeneous Learning from Demonstration. Correlated Adversarial Imitation Learning. Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning. Distant Supervision and Noisy Label Learning for Low Resource Na …
Estimating and abstracting the 3D structure of bones using neural networks on X-ray (2D) images
| Title | Estimating and abstracting the 3D structure of bones using neural networks on X-ray (2D) images |
| Authors | Jana Čavojská, Julian Petrasch, Nicolas J. Lehmann, Agnès Voisard, Peter Böttcher |
| Abstract | In this paper, we present a deep-learning based method for estimating the 3D structure of a bone from a pair of 2D X-ray images. Our triplet loss-trained neural network selects the most closely matching 3D bone shape from a predefined set of shapes. Our predictions have an average root mean square (RMS) distance of 1.08 mm between the predicted and true shapes, making it more accurate than the average error achieved by eight other examined 3D bone reconstruction approaches. The prediction process that we use is fully automated and unlike many competing approaches, it does not rely on any previous knowledge about bone geometry. Additionally, our neural network can determine the identity of a bone based only on its X-ray image. It computes a low-dimensional representation (“embedding”) of each 2D X-ray image and henceforth compares different X-ray images based only on their embeddings. An embedding holds enough information to uniquely identify the bone CT belonging to the input X-ray image with a 100% accuracy and can therefore serve as a kind of fingerprint for that bone. Possible applications include faster, image content-based bone database searches for forensic purposes. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.11499v1 |
| https://arxiv.org/pdf/2001.11499v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-and-abstracting-the-3d-structure |
| Repo | |
| Framework | |
Heterogeneous Learning from Demonstration
| Title | Heterogeneous Learning from Demonstration |
| Authors | Rohan Paleja, Matthew Gombolay |
| Abstract | The development of human-robot systems able to leverage the strengths of both humans and their robotic counterparts has been greatly sought after because of the foreseen, broad-ranging impact across industry and research. We believe the true potential of these systems cannot be reached unless the robot is able to act with a high level of autonomy, reducing the burden of manual tasking or teleoperation. To achieve this level of autonomy, robots must be able to work fluidly with its human partners, inferring their needs without explicit commands. This inference requires the robot to be able to detect and classify the heterogeneity of its partners. We propose a framework for learning from heterogeneous demonstration based upon Bayesian inference and evaluate a suite of approaches on a real-world dataset of gameplay from StarCraft II. This evaluation provides evidence that our Bayesian approach can outperform conventional methods by up to 12.8$%$. |
| Tasks | Bayesian Inference, Starcraft, Starcraft II |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.09569v1 |
| https://arxiv.org/pdf/2001.09569v1.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-learning-from-demonstration |
| Repo | |
| Framework | |
Correlated Adversarial Imitation Learning
| Title | Correlated Adversarial Imitation Learning |
| Authors | Ari Azarafrooz |
| Abstract | A novel imitation learning algorithm is introduced by applying a game-theoretic notion of correlated equilibrium to the generative adversarial imitation learning. This imitation learning algorithm is equipped with queues of discriminators and agents, in contrast with the classical approach, where there are single discriminator and single agent. The achievement of a correlated equilibrium is due to a mediating neural architecture, which augments the observations that are being seen by queues of discriminators and agents. At every step of the training, the mediator network computes feedback using the rewards of discriminators and agents, to augment the next observations accordingly. By interacting in the game, it steers the training dynamic towards more suitable regions. The resulting imitation learning provides three important benefits. First, it makes adaptability and transferability of the learned model to new environments straightforward. Second, it is suitable for imitating a mixture of state-action trajectories. Third, it avoids the difficulties of non-convex optimization faced by the discriminator in the generative adversarial type architectures. |
| Tasks | Imitation Learning |
| Published | 2020-02-16 |
| URL | https://arxiv.org/abs/2002.06476v1 |
| https://arxiv.org/pdf/2002.06476v1.pdf | |
| PWC | https://paperswithcode.com/paper/correlated-adversarial-imitation-learning |
| Repo | |
| Framework | |
Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning
| Title | Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning |
| Authors | Yannick Schroecker, Charles Isbell |
| Abstract | This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and does not suffer from hindsight bias in stochastic domains. As our second contribution, we extend the approach to imitation learning and show that it achieves state-of-the art demonstration sample-efficiency on standard benchmark tasks. |
| Tasks | Density Estimation, Imitation Learning |
| Published | 2020-02-15 |
| URL | https://arxiv.org/abs/2002.06473v1 |
| https://arxiv.org/pdf/2002.06473v1.pdf | |
| PWC | https://paperswithcode.com/paper/universal-value-density-estimation-for |
| Repo | |
| Framework | |
Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
| Title | Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá |
| Authors | David Ifeoluwa Adelani, Michael A. Hedderich, Dawei Zhu, Esther van den Berg, Dietrich Klakow |
| Abstract | The lack of labeled training data has limited the development of natural language processing tools, such as named entity recognition, for many languages spoken in developing countries. Techniques such as distant and weak supervision can be used to create labeled data in a (semi-) automatic way. Additionally, to alleviate some of the negative effects of the errors in automatic annotation, noise-handling methods can be integrated. Pretrained word embeddings are another key component of most neural named entity classifiers. With the advent of more complex contextual word embeddings, an interesting trade-off between model size and performance arises. While these techniques have been shown to work well in high-resource settings, we want to study how they perform in low-resource scenarios. In this work, we perform named entity recognition for Hausa and Yor`ub'a, two languages that are widely spoken in several developing countries. We evaluate different embedding approaches and show that distant supervision can be successfully leveraged in a realistic low-resource scenario where it can more than double a classifier’s performance. |
| Tasks | Named Entity Recognition, Word Embeddings |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08370v2 |
| https://arxiv.org/pdf/2003.08370v2.pdf | |
| PWC | https://paperswithcode.com/paper/distant-supervision-and-noisy-label-learning |
| Repo | |
| Framework | |
A New Clustering neural network for Chinese word segmentation
| Title | A New Clustering neural network for Chinese word segmentation |
| Authors | Yuze Zhao |
| Abstract | In this article I proposed a new model to achieve Chinese word segmentation(CWS),which may have the potentiality to apply in other domains in the future.It is a new thinking in CWS compared to previous works,to consider it as a clustering problem instead of a labeling problem.In this model,LSTM and self attention structures are used to collect context also sentence level features in every layer,and after several layers,a clustering model is applied to split characters into groups,which are the final segmentation results.I call this model CLNN.This algorithm can reach 98 percent of F score (without OOV words) and 85 percent to 95 percent F score (with OOV words) in training data sets.Error analyses shows that OOV words will greatly reduce performances,which needs a deeper research in the future. |
| Tasks | Chinese Word Segmentation |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07458v1 |
| https://arxiv.org/pdf/2002.07458v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-clustering-neural-network-for-chinese |
| Repo | |
| Framework | |
Latent Factor Analysis of Gaussian Distributions under Graphical Constraints
| Title | Latent Factor Analysis of Gaussian Distributions under Graphical Constraints |
| Authors | Md Mahmudul Hasan, Shuangqing Wei, Ali Moharrer |
| Abstract | We explore the algebraic structure of the solution space of convex optimization problem Constrained Minimum Trace Factor Analysis (CMTFA), when the population covariance matrix $\Sigma_x$ has an additional latent graphical constraint, namely, a latent star topology. In particular, we have shown that CMTFA can have either a rank $ 1 $ or a rank $ n-1 $ solution and nothing in between. The special case of a rank $ 1 $ solution, corresponds to the case where just one latent variable captures all the dependencies among the observables, giving rise to a star topology. We found explicit conditions for both rank $ 1 $ and rank $n- 1$ solutions for CMTFA solution of $\Sigma_x$. As a basic attempt towards building a more general Gaussian tree, we have found a necessary and a sufficient condition for multiple clusters, each having rank $ 1 $ CMTFA solution, to satisfy a minimum probability to combine together to build a Gaussian tree. To support our analytical findings we have presented some numerical demonstrating the usefulness of the contributions of our work. |
| Tasks | |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02712v2 |
| https://arxiv.org/pdf/2001.02712v2.pdf | |
| PWC | https://paperswithcode.com/paper/latent-factor-analysis-of-gaussian |
| Repo | |
| Framework | |
New advances in enumerative biclustering algorithms with online partitioning
| Title | New advances in enumerative biclustering algorithms with online partitioning |
| Authors | Rosana Veroneze, Fernando J. Von Zuben |
| Abstract | This paper further extends RIn-Close_CVC, a biclustering algorithm capable of performing an efficient, complete, correct and non-redundant enumeration of maximal biclusters with constant values on columns in numerical datasets. By avoiding a priori partitioning and itemization of the dataset, RIn-Close_CVC implements an online partitioning, which is demonstrated here to guide to more informative biclustering results. The improved algorithm is called RIn-Close_CVC3, keeps those attractive properties of RIn-Close_CVC, as formally proved here, and is characterized by: a drastic reduction in memory usage; a consistent gain in runtime; additional ability to handle datasets with missing values; and additional ability to operate with attributes characterized by distinct distributions or even mixed data types. The experimental results include synthetic and real-world datasets used to perform scalability and sensitivity analyses. As a practical case study, a parsimonious set of relevant and interpretable mixed-attribute-type rules is obtained in the context of supervised descriptive pattern mining. |
| Tasks | |
| Published | 2020-03-07 |
| URL | https://arxiv.org/abs/2003.04726v1 |
| https://arxiv.org/pdf/2003.04726v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-advances-in-enumerative-biclustering |
| Repo | |
| Framework | |
Deep segmental phonetic posterior-grams based discovery of non-categories in L2 English speech
| Title | Deep segmental phonetic posterior-grams based discovery of non-categories in L2 English speech |
| Authors | Xu Li, Xixin Wu, Xunying Liu, Helen Meng |
| Abstract | Second language (L2) speech is often labeled with the native, phone categories. However, in many cases, it is difficult to decide on a categorical phone that an L2 segment belongs to. These segments are regarded as non-categories. Most existing approaches for Mispronunciation Detection and Diagnosis (MDD) are only concerned with categorical errors, i.e. a phone category is inserted, deleted or substituted by another. However, non-categorical errors are not considered. To model these non-categorical errors, this work aims at exploring non-categorical patterns to extend the categorical phone set. We apply a phonetic segment classifier to generate segmental phonetic posterior-grams (SPPGs) to represent phone segment-level information. And then we explore the non-categories by looking for the SPPGs with more than one peak. Compared with the baseline system, this approach explores more non-categorical patterns, and also perceptual experimental results show that the explored non-categories are more accurate with increased confusion degree by 7.3% and 7.5% under two different measures. Finally, we preliminarily analyze the reason behind those non-categories. |
| Tasks | |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.00205v1 |
| https://arxiv.org/pdf/2002.00205v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-segmental-phonetic-posterior-grams-based |
| Repo | |
| Framework | |
Opportunities of a Machine Learning-based Decision Support System for Stroke Rehabilitation Assessment
| Title | Opportunities of a Machine Learning-based Decision Support System for Stroke Rehabilitation Assessment |
| Authors | Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez i Badia |
| Abstract | Rehabilitation assessment is critical to determine an adequate intervention for a patient. However, the current practices of assessment mainly rely on therapist’s experience, and assessment is infrequently executed due to the limited availability of a therapist. In this paper, we identified the needs of therapists to assess patient’s functional abilities (e.g. alternative perspective on assessment with quantitative information on patient’s exercise motions). As a result, we developed an intelligent decision support system that can identify salient features of assessment using reinforcement learning to assess the quality of motion and summarize patient specific analysis. We evaluated this system with seven therapists using the dataset from 15 patient performing three exercises. The evaluation demonstrates that our system is preferred over a traditional system without analysis while presenting more useful information and significantly increasing the agreement over therapists’ evaluation from 0.6600 to 0.7108 F1-scores ($p <0.05$). We discuss the importance of presenting contextually relevant and salient information and adaptation to develop a human and machine collaborative decision making system. |
| Tasks | Decision Making |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12261v2 |
| https://arxiv.org/pdf/2002.12261v2.pdf | |
| PWC | https://paperswithcode.com/paper/opportunities-of-a-machine-learning-based |
| Repo | |
| Framework | |
Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey
| Title | Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey |
| Authors | Zahra Abbasiyantaeb, Saeedeh Momtazi |
| Abstract | Text-based Question Answering (QA) is a challenging task which aims at finding short concrete answers for users’ questions. This line of research has been widely studied with information retrieval techniques and has received increasing attention in recent years by considering deep neural network approaches. Deep learning approaches, which are the main focus of this paper, provide a powerful technique to learn multiple layers of representations and interaction between questions and texts. In this paper, we provide a comprehensive overview of different models proposed for the QA task, including both traditional information retrieval perspective, and more recent deep neural network perspective. We also introduce well-known datasets for the task and present available results from the literature to have a comparison between different techniques. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2020-02-16 |
| URL | https://arxiv.org/abs/2002.06612v1 |
| https://arxiv.org/pdf/2002.06612v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-based-question-answering-from |
| Repo | |
| Framework | |
Historical Document Processing: Historical Document Processing: A Survey of Techniques, Tools, and Trends
| Title | Historical Document Processing: Historical Document Processing: A Survey of Techniques, Tools, and Trends |
| Authors | James P. Philips, Nasseh Tabrizi |
| Abstract | Historical Document Processing is the process of digitizing written material from the past for future use by historians and other scholars. It incorporates algorithms and software tools from various subfields of computer science, including computer vision, document analysis and recognition, natural language processing, and machine learning, to convert images of ancient manuscripts, letters, diaries, and early printed texts automatically into a digital format usable in data mining and information retrieval systems. Within the past twenty years, as libraries, museums, and other cultural heritage institutions have scanned an increasing volume of their historical document archives, the need to transcribe the full text from these collections has become acute. Since Historical Document Processing encompasses multiple sub-domains of computer science, knowledge relevant to its purpose is scattered across numerous journals and conference proceedings. This paper surveys the major phases of, standard algorithms, tools, and datasets in the field of Historical Document Processing, discusses the results of a literature review, and finally suggests directions for further research. |
| Tasks | Information Retrieval |
| Published | 2020-02-15 |
| URL | https://arxiv.org/abs/2002.06300v1 |
| https://arxiv.org/pdf/2002.06300v1.pdf | |
| PWC | https://paperswithcode.com/paper/historical-document-processing-historical |
| Repo | |
| Framework | |
An Equivalence Between Private Classification and Online Prediction
| Title | An Equivalence Between Private Classification and Online Prediction |
| Authors | Mark Bun, Roi Livni, Shay Moran |
| Abstract | We prove that every concept class with finite Littlestone dimension can be learned by an (approximate) differentially-private algorithm. This answers an open question of Alon et al. (STOC 2019) who proved the converse statement (this question was also asked by Neel et al.~(FOCS 2019)). Together these two results yield an equivalence between online learnability and private PAC learnability. We introduce a new notion of algorithmic stability called “global stability” which is essential to our proof and may be of independent interest. We also discuss an application of our results to boosting the privacy and accuracy parameters of differentially-private learners. |
| Tasks | |
| Published | 2020-03-01 |
| URL | https://arxiv.org/abs/2003.00563v2 |
| https://arxiv.org/pdf/2003.00563v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-equivalence-between-private-classification |
| Repo | |
| Framework | |
Generalized mean shift with triangular kernel profile
| Title | Generalized mean shift with triangular kernel profile |
| Authors | Sébastien Razakarivony, Axel Barrau |
| Abstract | The mean shift algorithm is a popular way to find modes of some probability density functions taking a specific kernel-based shape, used for clustering or visual tracking. Since its introduction, it underwent several practical improvements and generalizations, as well as deep theoretical analysis mainly focused on its convergence properties. In spite of encouraging results, this question has not received a clear general answer yet. In this paper we focus on a specific class of kernels, adapted in particular to the distributions clustering applications which motivated this work. We show that a novel Mean Shift variant adapted to them can be derived, and proved to converge after a finite number of iterations. In order to situate this new class of methods in the general picture of the Mean Shift theory, we alo give a synthetic exposure of existing results of this field. |
| Tasks | Visual Tracking |
| Published | 2020-01-07 |
| URL | https://arxiv.org/abs/2001.02165v1 |
| https://arxiv.org/pdf/2001.02165v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-mean-shift-with-triangular-kernel |
| Repo | |
| Framework | |
Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes
| Title | Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes |
| Authors | Tomas Brazdil, Krishnendu Chatterjee, Petr Novotny, Jiri Vahala |
| Abstract | Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which ignores low probability catastrophic events withhighly negative impact on the system. On the other hand,risk-averse policies require the probability of undesirableevents to be below a given threshold, but they do not accountfor optimization of the expected payoff. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. The objective of risk-constrainedplanning is to maximize the expected discounted-sum payoffamong risk-averse policies that ensure the probability to en-counter a failure state is below a desired threshold. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP (in the style of AlphaZero)and with a risk-constrained action selection via linear pro-gramming. We demonstrate the effectiveness of our approachwith experiments on classical MDPs from the literature, in-cluding benchmarks with an order of 10^6 states. |
| Tasks | Decision Making |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12086v1 |
| https://arxiv.org/pdf/2002.12086v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-of-risk-constrained |
| Repo | |
| Framework | |
