Paper Group ANR 1206
Lattice-Based Fuzzy Medical Expert System for Low Back Pain Management. Real-time Anomaly Detection and Classification in Streaming PMU Data. Informed Machine Learning – A Taxonomy and Survey of Integrating Knowledge into Learning Systems. Naver at ActivityNet Challenge 2019 – Task B Active Speaker Detection (AVA). Optimizer Benchmarking Needs to …
Lattice-Based Fuzzy Medical Expert System for Low Back Pain Management
| Title | Lattice-Based Fuzzy Medical Expert System for Low Back Pain Management |
| Authors | Debarpita Santra, S. K. Basu, J. K. Mondal, Subrata Goswami |
| Abstract | Low Back Pain (LBP) is a common medical condition that deprives many individuals worldwide of their normal routine activities. In the absence of external biomarkers, diagnosis of LBP is quite challenging. It requires dealing with several clinical variables, which have no precisely quantified values. Aiming at the development of a fuzzy medical expert system for LBP management, this research proposes an attractive lattice-based knowledge representation scheme for handling imprecision in knowledge, offering a suitable design methodology for a fuzzy knowledge base and a fuzzy inference system. The fuzzy knowledge base is constructed in modular fashion, with each module capturing interrelated medical knowledge about the relevant clinical history, clinical examinations and laboratory investigation results. This approach in design ensures optimality, consistency and preciseness in the knowledge base and scalability. The fuzzy inference system, which uses the Mamdani method, adopts the triangular membership function for fuzzification and the Centroid of Area technique for defuzzification. A prototype of this system has been built using the knowledge extracted from the domain expert physicians. The inference of the system against a few available patient records at the ESI Hospital, Sealdah has been checked. It was found to be acceptable by the verifying medical experts. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03983v1 |
| https://arxiv.org/pdf/1909.03983v1.pdf | |
| PWC | https://paperswithcode.com/paper/lattice-based-fuzzy-medical-expert-system-for |
| Repo | |
| Framework | |
Real-time Anomaly Detection and Classification in Streaming PMU Data
| Title | Real-time Anomaly Detection and Classification in Streaming PMU Data |
| Authors | Christopher Hannon, Deepjyoti Deka, Dong Jin, Marc Vuffray, Andrey Y. Lokhov |
| Abstract | Ensuring secure and reliable operations of the power grid is a primary concern of system operators. Phasor measurement units (PMUs) are rapidly being deployed in the grid to provide fast-sampled operational data that should enable quicker decision-making. This work presents a general interpretable framework for analyzing real-time PMU data, and thus enabling grid operators to understand the current state and to identify anomalies on the fly. Applying statistical learning tools on the streaming data, we first learn an effective dynamical model to describe the current behavior of the system. Next, we use the probabilistic predictions of our learned model to define in a principled way an efficient anomaly detection tool. Finally, the last module of our framework produces on-the-fly classification of the detected anomalies into common occurrence classes using features that grid operators are familiar with. We demonstrate the efficacy of our interpretable approach through extensive numerical experiments on real PMU data collected from a transmission operator in the USA. |
| Tasks | Anomaly Detection, Decision Making |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06316v1 |
| https://arxiv.org/pdf/1911.06316v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-anomaly-detection-and |
| Repo | |
| Framework | |
Informed Machine Learning – A Taxonomy and Survey of Integrating Knowledge into Learning Systems
| Title | Informed Machine Learning – A Taxonomy and Survey of Integrating Knowledge into Learning Systems |
| Authors | Laura von Rueden, Sebastian Mayer, Katharina Beckh, Bogdan Georgiev, Sven Giesselbach, Raoul Heese, Birgit Kirsch, Julius Pfrommer, Annika Pick, Rajkumar Ramamurthy, Michal Walczak, Jochen Garcke, Christian Bauckhage, Jannis Schuecker |
| Abstract | Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process, which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. First, we provide a definition and propose a concept for informed machine learning, which illustrates its building blocks and distinguishes it from conventional machine learning. Second, we introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Third, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning. |
| Tasks | |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1903.12394v2 |
| https://arxiv.org/pdf/1903.12394v2.pdf | |
| PWC | https://paperswithcode.com/paper/informed-machine-learning-towards-a-taxonomy |
| Repo | |
| Framework | |
Naver at ActivityNet Challenge 2019 – Task B Active Speaker Detection (AVA)
| Title | Naver at ActivityNet Challenge 2019 – Task B Active Speaker Detection (AVA) |
| Authors | Joon Son Chung |
| Abstract | This report describes our submission to the ActivityNet Challenge at CVPR 2019. We use a 3D convolutional neural network (CNN) based front-end and an ensemble of temporal convolution and LSTM classifiers to predict whether a visible person is speaking or not. Our results show significant improvements over the baseline on the AVA-ActiveSpeaker dataset. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10555v1 |
| https://arxiv.org/pdf/1906.10555v1.pdf | |
| PWC | https://paperswithcode.com/paper/naver-at-activitynet-challenge-2019-task-b |
| Repo | |
| Framework | |
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning
| Title | Optimizer Benchmarking Needs to Account for Hyperparameter Tuning |
| Authors | Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi, François Fleuret |
| Abstract | The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparameters, and finding these settings may be prohibitively costly for practitioners. In this work, we argue that a fair assessment of optimizers’ performance must take the computational cost of hyperparameter tuning into account, i.e., how easy it is to find good hyperparameter configurations using an automatic hyperparameter search. Evaluating a variety of optimizers on an extensive set of standard datasets and architectures, our results indicate that Adam is the most practical solution, particularly in low-budget scenarios. |
| Tasks | |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11758v3 |
| https://arxiv.org/pdf/1910.11758v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-tunability-of-optimizers-in-deep |
| Repo | |
| Framework | |
Convergence of Parameter Estimates for Regularized Mixed Linear Regression Models
| Title | Convergence of Parameter Estimates for Regularized Mixed Linear Regression Models |
| Authors | Taiyao Wang, Ioannis Ch. Paschalidis |
| Abstract | We consider {\em Mixed Linear Regression (MLR)}, where training data have been generated from a mixture of distinct linear models (or clusters) and we seek to identify the corresponding coefficient vectors. We introduce a {\em Mixed Integer Programming (MIP)} formulation for MLR subject to regularization constraints on the coefficient vectors. We establish that as the number of training samples grows large, the MIP solution converges to the true coefficient vectors in the absence of noise. Subject to slightly stronger assumptions, we also establish that the MIP identifies the clusters from which the training samples were generated. In the special case where training data come from a single cluster, we establish that the corresponding MIP yields a solution that converges to the true coefficient vector even when training data are perturbed by (martingale difference) noise. We provide a counterexample indicating that in the presence of noise, the MIP may fail to produce the true coefficient vectors for more than one clusters. We also provide numerical results testing the MIP solutions in synthetic examples with noise. |
| Tasks | |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09235v2 |
| https://arxiv.org/pdf/1903.09235v2.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-of-parameter-estimates-for |
| Repo | |
| Framework | |
Towards Design Space Exploration and Optimization of Fast Algorithms for Convolutional Neural Networks (CNNs) on FPGAs
| Title | Towards Design Space Exploration and Optimization of Fast Algorithms for Convolutional Neural Networks (CNNs) on FPGAs |
| Authors | Afzal Ahmad, Muhammad Adeel Pasha |
| Abstract | Convolutional Neural Networks (CNNs) have gained widespread popularity in the field of computer vision and image processing. Due to huge computational requirements of CNNs, dedicated hardware-based implementations are being explored to improve their performance. Hardware platforms such as Field Programmable Gate Arrays (FPGAs) are widely being used to design parallel architectures for this purpose. In this paper, we analyze Winograd minimal filtering or fast convolution algorithms to reduce the arithmetic complexity of convolutional layers of CNNs. We explore a complex design space to find the sets of parameters that result in improved throughput and power-efficiency. We also design a pipelined and parallel Winograd convolution engine that improves the throughput and power-efficiency while reducing the computational complexity of the overall system. Our proposed designs show up to 4.75$\times$ and 1.44$\times$ improvements in throughput and power-efficiency, respectively, in comparison to the state-of-the-art design while using approximately 2.67$\times$ more multipliers. Furthermore, we obtain savings of up to 53.6% in logic resources compared with the state-of-the-art implementation. |
| Tasks | |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01811v1 |
| http://arxiv.org/pdf/1903.01811v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-design-space-exploration-and |
| Repo | |
| Framework | |
FAKTA: An Automatic End-to-End Fact Checking System
| Title | FAKTA: An Automatic End-to-End Fact Checking System |
| Authors | Moin Nadeem, Wei Fang, Brian Xu, Mitra Mohtarami, James Glass |
| Abstract | We present FAKTA which is a unified framework that integrates various components of a fact checking process: document retrieval from media sources with various types of reliability, stance detection of documents with respect to given claims, evidence extraction, and linguistic analysis. FAKTA predicts the factuality of given claims and provides evidence at the document and sentence level to explain its predictions |
| Tasks | Stance Detection |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.04164v1 |
| https://arxiv.org/pdf/1906.04164v1.pdf | |
| PWC | https://paperswithcode.com/paper/fakta-an-automatic-end-to-end-fact-checking-1 |
| Repo | |
| Framework | |
Magic: The Gathering is Turing Complete
| Title | Magic: The Gathering is Turing Complete |
| Authors | Alex Churchill, Stella Biderman, Austin Herrick |
| Abstract | $\textit{Magic: The Gathering}$ is a popular and famously complicated trading card game about magical combat. In this paper we show that optimal play in real-world $\textit{Magic}$ is at least as hard as the Halting Problem, solving a problem that has been open for a decade. To do this, we present a methodology for embedding an arbitrary Turing machine into a game of $\textit{Magic}$ such that the first player is guaranteed to win the game if and only if the Turing machine halts. Our result applies to how real $\textit{Magic}$ is played, can be achieved using standard-size tournament-legal decks, and does not rely on stochasticity or hidden information. Our result is also highly unusual in that all moves of both players are forced in the construction. This shows that even recognising who will win a game in which neither player has a non-trivial decision to make for the rest of the game is undecidable. We conclude with a discussion of the implications for a unified computational theory of games and remarks about the playability of such a board in a tournament setting. |
| Tasks | |
| Published | 2019-03-24 |
| URL | http://arxiv.org/abs/1904.09828v2 |
| http://arxiv.org/pdf/1904.09828v2.pdf | |
| PWC | https://paperswithcode.com/paper/190409828 |
| Repo | |
| Framework | |
Neuro-Optimization: Learning Objective Functions Using Neural Networks
| Title | Neuro-Optimization: Learning Objective Functions Using Neural Networks |
| Authors | Younghan Jeon, Minsik Lee, Jin Young Choi |
| Abstract | Mathematical optimization is widely used in various research fields. With a carefully-designed objective function, mathematical optimization can be quite helpful in solving many problems. However, objective functions are usually hand-crafted and designing a good one can be quite challenging. In this paper, we propose a novel framework to learn the objective function based on a neural net-work. The basic idea is to consider the neural network as an objective function, and the input as an optimization variable. For the learning of objective function from the training data, two processes are conducted: In the inner process, the optimization variable (the input of the network) are optimized to minimize the objective function (the network output), while fixing the network weights. In the outer process, on the other hand, the weights are optimized based on how close the final solution of the inner process is to the desired solution. After learning the objective function, the solution for the test set is obtained in the same manner of the inner process. The potential and applicability of our approach are demonstrated by the experiments on toy examples and a computer vision task, optical flow. |
| Tasks | Optical Flow Estimation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10079v1 |
| https://arxiv.org/pdf/1905.10079v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuro-optimization-learning-objective |
| Repo | |
| Framework | |
Field of View Extension in Computed Tomography Using Deep Learning Prior
| Title | Field of View Extension in Computed Tomography Using Deep Learning Prior |
| Authors | Yixing Huang, Lei Gao, Alexander Preuhs, Andreas Maier |
| Abstract | In computed tomography (CT), data truncation is a common problem. Images reconstructed by the standard filtered back-projection algorithm from truncated data suffer from cupping artifacts inside the field-of-view (FOV), while anatomical structures are severely distorted or missing outside the FOV. Deep learning, particularly the U-Net, has been applied to extend the FOV as a post-processing method. Since image-to-image prediction neglects the data fidelity to measured projection data, incorrect structures, even inside the FOV, might be reconstructed by such an approach. Therefore, generating reconstructed images directly from a post-processing neural network is inadequate. In this work, we propose a data consistent reconstruction method, which utilizes deep learning reconstruction as prior for extrapolating truncated projections and a conventional iterative reconstruction to constrain the reconstruction consistent to measured raw data. Its efficacy is demonstrated in our study, achieving small average root-mean-square error of 24 HU inside the FOV and a high structure similarity index of 0.993 for the whole body area on a test patient’s CT data. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01178v2 |
| https://arxiv.org/pdf/1911.01178v2.pdf | |
| PWC | https://paperswithcode.com/paper/field-of-view-extension-in-computed |
| Repo | |
| Framework | |
Classification Calibration for Long-tail Instance Segmentation
| Title | Classification Calibration for Long-tail Instance Segmentation |
| Authors | Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Jun Hao Liew, Sheng Tang, Steven Hoi, Jiashi Feng |
| Abstract | Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balanced and class-limited benchmarks, such as Microsoft COCO dataset [8]. In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals. Based on this observation, we propose to calibrate the prediction of classification head to improve recognition performance for the tail classes. Without much additional cost and modification of the detection model architecture, our calibration method improves the performance of the baseline by a large margin on the tail classes. Codes will be available. Importantly, after the submission, we find significant improvement can be further achieved by modifying the calibration head, which we will update later. |
| Tasks | Calibration, Instance Segmentation, Semantic Segmentation |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13081v2 |
| https://arxiv.org/pdf/1910.13081v2.pdf | |
| PWC | https://paperswithcode.com/paper/classification-calibration-for-long-tail |
| Repo | |
| Framework | |
Towards Good Practices for Instance Segmentation
| Title | Towards Good Practices for Instance Segmentation |
| Authors | Dongdong Yu, Zehuan Yuan, Jinlai Liu, Kun Yuan, Changhu Wang |
| Abstract | Instance Segmentation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the Hybrid Task Cascade (HTC) Network, and empirically evaluate their impact on the final model performance through ablation studies. By taking all the refinements, we achieve 0.47 on the COCO test-dev dataset and 0.47 on the COCO test-challenge dataset. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1911.07939v1 |
| https://arxiv.org/pdf/1911.07939v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-good-practices-for-instance |
| Repo | |
| Framework | |
Team PFDet’s Methods for Open Images Challenge 2019
| Title | Team PFDet’s Methods for Open Images Challenge 2019 |
| Authors | Yusuke Niitani, Toru Ogawa, Shuji Suzuki, Takuya Akiba, Tommi Kerola, Kohei Ozaki, Shotaro Sano |
| Abstract | We present the instance segmentation and the object detection method used by team PFDet for Open Images Challenge 2019. We tackle a massive dataset size, huge class imbalance and federated annotations. Using this method, the team PFDet achieved 3rd and 4th place in the instance segmentation and the object detection track, respectively. |
| Tasks | Instance Segmentation, Object Detection, Semantic Segmentation |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11534v1 |
| https://arxiv.org/pdf/1910.11534v1.pdf | |
| PWC | https://paperswithcode.com/paper/team-pfdets-methods-for-open-images-challenge |
| Repo | |
| Framework | |
Image Colorization By Capsule Networks
| Title | Image Colorization By Capsule Networks |
| Authors | Gökhan Özbulak |
| Abstract | In this paper, a simple topology of Capsule Network (CapsNet) is investigated for the problem of image colorization. The generative and segmentation capabilities of the original CapsNet topology, which is proposed for image classification problem, is leveraged for the colorization of the images by modifying the network as follows:1) The original CapsNet model is adapted to map the grayscale input to the output in the CIE Lab colorspace, 2) The feature detector part of the model is updated by using deeper feature layers inherited from VGG-19 pre-trained model with weights in order to transfer low-level image representation capability to this model, 3) The margin loss function is modified as Mean Squared Error (MSE) loss to minimize the image-to-imagemapping. The resulting CapsNet model is named as Colorizer Capsule Network (ColorCapsNet).The performance of the ColorCapsNet is evaluated on the DIV2K dataset and promising results are obtained to investigate Capsule Networks further for image colorization problem. |
| Tasks | Colorization, Image Classification |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08307v1 |
| https://arxiv.org/pdf/1908.08307v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-colorization-by-capsule-networks |
| Repo | |
| Framework | |
