Paper Group ANR 621
Fundamental limits of detection in the spiked Wigner model. Lip Reading Using Convolutional Auto Encoders as Feature Extractor. A Collaborative Approach to Angel and Venture Capital Investment Recommendations. Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models. Predictive Uncertainty Estimation via Pri …
Fundamental limits of detection in the spiked Wigner model
| Title | Fundamental limits of detection in the spiked Wigner model |
| Authors | Ahmed El Alaoui, Florent Krzakala, Michael I. Jordan |
| Abstract | We study the fundamental limits of detecting the presence of an additive rank-one perturbation, or spike, to a Wigner matrix. When the spike comes from a prior that is i.i.d. across coordinates, we prove that the log-likelihood ratio of the spiked model against the non-spiked one is asymptotically normal below a certain reconstruction threshold which is not necessarily of a “spectral” nature, and that it is degenerate above. This establishes the maximal region of contiguity between the planted and null models. It is known that this threshold also marks a phase transition for estimating the spike: the latter task is possible above the threshold and impossible below. Therefore, both estimation and detection undergo the same transition in this random matrix model. We also provide further information about the performance of the optimal test. Our proofs are based on Gaussian interpolation methods and a rigorous incarnation of the cavity method, as devised by Guerra and Talagrand in their study of the Sherrington–Kirkpatrick spin-glass model. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09588v1 |
| http://arxiv.org/pdf/1806.09588v1.pdf | |
| PWC | https://paperswithcode.com/paper/fundamental-limits-of-detection-in-the-spiked |
| Repo | |
| Framework | |
Lip Reading Using Convolutional Auto Encoders as Feature Extractor
| Title | Lip Reading Using Convolutional Auto Encoders as Feature Extractor |
| Authors | Dharin Parekh, Ankitesh Gupta, Shharrnam Chhatpar, Anmol Yash Kumar, Manasi Kulkarni |
| Abstract | Visual recognition of speech using the lip movement is called Lip-reading. Recent developments in this nascent field uses different neural networks as feature extractors which serve as input to a model which can map the temporal relationship and classify. Though end to end sentence level Lip-reading is the current trend, we proposed a new model which employs word level classification and breaks the set benchmarks for standard datasets. In our model we use convolutional autoencoders as feature extractors which are then fed to a Long short-term memory model. We tested our proposed model on BBC’s LRW dataset, MIRACL-VC1 and GRID dataset. Achieving a classification accuracy of 98% on MIRACL-VC1 as compared to 93.4% of the set benchmark (Rekik et al., 2014). On BBC’s LRW the proposed model performed better than the baseline model of convolutional neural networks and Long short-term memory model (Garg et al., 2016). Showing the features learned by the models we clearly indicate how the proposed model works better than the baseline model. The same model can also be extended for end to end sentence level classification. |
| Tasks | |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12371v1 |
| http://arxiv.org/pdf/1805.12371v1.pdf | |
| PWC | https://paperswithcode.com/paper/lip-reading-using-convolutional-auto-encoders |
| Repo | |
| Framework | |
A Collaborative Approach to Angel and Venture Capital Investment Recommendations
| Title | A Collaborative Approach to Angel and Venture Capital Investment Recommendations |
| Authors | Xinyi Liu, Artit Wangperawong |
| Abstract | Matrix factorization was used to generate investment recommendations for investors. An iterative conjugate gradient method was used to optimize the regularized squared-error loss function. The number of latent factors, number of iterations, and regularization values were explored. Overfitting can be addressed by either early stopping or regularization parameter tuning. The model achieved the highest average prediction accuracy of 13.3%. With a similar model, the same dataset was used to generate investor recommendations for companies undergoing fundraising, which achieved highest prediction accuracy of 11.1%. |
| Tasks | |
| Published | 2018-07-26 |
| URL | http://arxiv.org/abs/1807.09967v1 |
| http://arxiv.org/pdf/1807.09967v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-collaborative-approach-to-angel-and-venture |
| Repo | |
| Framework | |
Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models
| Title | Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models |
| Authors | Henry Elder, Chris Hokamp |
| Abstract | This work presents a new state of the art in reconstruction of surface realizations from obfuscated text. We identify the lack of sufficient training data as the major obstacle to training high-performing models, and solve this issue by generating large amounts of synthetic training data. We also propose preprocessing techniques which make the structure contained in the input features more accessible to sequence models. Our models were ranked first on all evaluation metrics in the English portion of the 2018 Surface Realization shared task. |
| Tasks | Data Augmentation |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07731v1 |
| http://arxiv.org/pdf/1805.07731v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-high-quality-surface-realizations |
| Repo | |
| Framework | |
Predictive Uncertainty Estimation via Prior Networks
| Title | Predictive Uncertainty Estimation via Prior Networks |
| Authors | Andrey Malinin, Mark Gales |
| Abstract | Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Different actions might be taken depending on the source of the uncertainty so it is important to be able to distinguish between them. Recently, baseline tasks and metrics have been defined and several practical methods to estimate uncertainty developed. These methods, however, attempt to model uncertainty due to distributional mismatch either implicitly through model uncertainty or as data uncertainty. This work proposes a new framework for modeling predictive uncertainty called Prior Networks (PNs) which explicitly models distributional uncertainty. PNs do this by parameterizing a prior distribution over predictive distributions. This work focuses on uncertainty for classification and evaluates PNs on the tasks of identifying out-of-distribution (OOD) samples and detecting misclassification on the MNIST dataset, where they are found to outperform previous methods. Experiments on synthetic and MNIST and CIFAR-10 data show that unlike previous non-Bayesian methods PNs are able to distinguish between data and distributional uncertainty. |
| Tasks | |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1802.10501v4 |
| http://arxiv.org/pdf/1802.10501v4.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-uncertainty-estimation-via-prior |
| Repo | |
| Framework | |
Toward the Engineering of Virtuous Machines
| Title | Toward the Engineering of Virtuous Machines |
| Authors | Naveen Sundar Govindarajulu, Selmer Bringsjord, Rikhiya Ghosh |
| Abstract | While various traditions under the ‘virtue ethics’ umbrella have been studied extensively and advocated by ethicists, it has not been clear that there exists a version of virtue ethics rigorous enough to be a target for machine ethics (which we take to include the engineering of an ethical sensibility in a machine or robot itself, not only the study of ethics in the humans who might create artificial agents). We begin to address this by presenting an embryonic formalization of a key part of any virtue-ethics theory: namely, the learning of virtue by a focus on exemplars of moral virtue. Our work is based in part on a computational formal logic previously used to formally model other ethical theories and principles therein, and to implement these models in artificial agents. |
| Tasks | |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.03868v2 |
| http://arxiv.org/pdf/1812.03868v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-the-engineering-of-virtuous-machines |
| Repo | |
| Framework | |
Method for motion artifact reduction using a convolutional neural network for dynamic contrast enhanced MRI of the liver
| Title | Method for motion artifact reduction using a convolutional neural network for dynamic contrast enhanced MRI of the liver |
| Authors | Daiki Tamada, Marie-Luise Kromrey, Hiroshi Onishi, Utaroh Motosugi |
| Abstract | Purpose: To improve the quality of images obtained via dynamic contrast-enhanced MRI (DCE-MRI) that include motion artifacts and blurring using a deep learning approach. Methods: A multi-channel convolutional neural network (MARC) based method is proposed for reducing the motion artifacts and blurring caused by respiratory motion in images obtained via DCE-MRI of the liver. The training datasets for the neural network included images with and without respiration-induced motion artifacts or blurring, and the distortions were generated by simulating the phase error in k-space. Patient studies were conducted using a multi-phase T1-weighted spoiled gradient echo sequence for the liver containing breath-hold failures during data acquisition. The trained network was applied to the acquired images to analyze the filtering performance, and the intensities and contrast ratios before and after denoising were compared via Bland-Altman plots. Results: The proposed network was found to significantly reduce the magnitude of the artifacts and blurring induced by respiratory motion, and the contrast ratios of the images after processing via the network were consistent with those of the unprocessed images. Conclusion: A deep learning based method for removing motion artifacts in images obtained via DCE-MRI in the liver was demonstrated and validated. |
| Tasks | Denoising |
| Published | 2018-07-18 |
| URL | http://arxiv.org/abs/1807.06956v2 |
| http://arxiv.org/pdf/1807.06956v2.pdf | |
| PWC | https://paperswithcode.com/paper/method-for-motion-artifact-reduction-using-a |
| Repo | |
| Framework | |
CRAFT: Complementary Recommendations Using Adversarial Feature Transformer
| Title | CRAFT: Complementary Recommendations Using Adversarial Feature Transformer |
| Authors | Cong Phuoc Huynh, Arridhana Ciptadi, Ambrish Tyagi, Amit Agrawal |
| Abstract | Traditional approaches for complementary product recommendations rely on behavioral and non-visual data such as customer co-views or co-buys. However, certain domains such as fashion are primarily visual. We propose a framework that harnesses visual cues in an unsupervised manner to learn the distribution of co-occurring complementary items in real world images. Our model learns a non-linear transformation between the two manifolds of source and target complementary item categories (e.g., tops and bottoms in outfits). Given a large dataset of images containing instances of co-occurring object categories, we train a generative transformer network directly on the feature representation space by casting it as an adversarial optimization problem. Such a conditional generative model can produce multiple novel samples of complementary items (in the feature space) for a given query item. The final recommendations are selected from the closest real world examples to the synthesized complementary features. We apply our framework to the task of recommending complementary tops for a given bottom clothing item. The recommendations made by our system are diverse, and are favored by human experts over the baseline approaches. |
| Tasks | |
| Published | 2018-04-29 |
| URL | http://arxiv.org/abs/1804.10871v3 |
| http://arxiv.org/pdf/1804.10871v3.pdf | |
| PWC | https://paperswithcode.com/paper/craft-complementary-recommendations-using |
| Repo | |
| Framework | |
A Novel Approach to Skew-Detection and Correction of English Alphabets for OCR
| Title | A Novel Approach to Skew-Detection and Correction of English Alphabets for OCR |
| Authors | Chinmay Chinara, Nishant Nath, Subhajeet Mishra, Sangram Keshari Sahoo, Farida Ashraf Ali |
| Abstract | Optical Character Recognition has been a challenging field in the advent of digital computers. It is needed where information is to be readable both to humans and machines. The process of OCR is composed of a set of pre and post processing steps that decide the level of accuracy of recognition. This paper deals with one of the pre-processing steps involved in the OCR process i.e. Skew (Slant) Detection and Correction. The proposed algorithm implemented for skew-detection is termed as the COG (Centre of Gravity) method and for that of skew-correction is Sub-Pixel Shifting method. The algorithm has been kept simple and optimized for efficient skew-detection and correction. The performance analysis of the algorithm after testing has been aptly demonstrated. |
| Tasks | Optical Character Recognition |
| Published | 2018-01-02 |
| URL | http://arxiv.org/abs/1801.00824v1 |
| http://arxiv.org/pdf/1801.00824v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-approach-to-skew-detection-and |
| Repo | |
| Framework | |
Simulation and Calibration of a Fully Bayesian Marked Multidimensional Hawkes Process with Dissimilar Decays
| Title | Simulation and Calibration of a Fully Bayesian Marked Multidimensional Hawkes Process with Dissimilar Decays |
| Authors | Kar Wai Lim, Young Lee, Leif Hanlen, Hongbiao Zhao |
| Abstract | We propose a simulation method for multidimensional Hawkes processes based on superposition theory of point processes. This formulation allows us to design efficient simulations for Hawkes processes with differing exponentially decaying intensities. We demonstrate that inter-arrival times can be decomposed into simpler auxiliary variables that can be sampled directly, giving exact simulation with no approximation. We establish that the auxiliary variables provides information on the parent process for each event time. The algorithm correctness is shown by verifying the simulated intensities with their theoretical moments. A modular inference procedure consisting of Gibbs samplers through the auxiliary variable augmentation and adaptive rejection sampling is presented. Finally, we compare our proposed simulation method against existing methods, and find significant improvement in terms of algorithm speed. Our inference algorithm is used to discover the strengths of mutually excitations in real dark networks. |
| Tasks | Calibration, Point Processes |
| Published | 2018-03-13 |
| URL | http://arxiv.org/abs/1803.04654v1 |
| http://arxiv.org/pdf/1803.04654v1.pdf | |
| PWC | https://paperswithcode.com/paper/simulation-and-calibration-of-a-fully |
| Repo | |
| Framework | |
Learning Individualized Cardiovascular Responses from Large-scale Wearable Sensors Data
| Title | Learning Individualized Cardiovascular Responses from Large-scale Wearable Sensors Data |
| Authors | Haraldur T. Hallgrímsson, Filip Jankovic, Tim Althoff, Luca Foschini |
| Abstract | We consider the problem of modeling cardiovascular responses to physical activity and sleep changes captured by wearable sensors in free living conditions. We use an attentional convolutional neural network to learn parsimonious signatures of individual cardiovascular response from data recorded at the minute level resolution over several months on a cohort of 80k people. We demonstrate internal validity by showing that signatures generated on an individual’s 2017 data generalize to predict minute-level heart rate from physical activity and sleep for the same individual in 2018, outperforming several time-series forecasting baselines. We also show external validity demonstrating that signatures outperform plain resting heart rate (RHR) in predicting variables associated with cardiovascular functions, such as age and Body Mass Index (BMI). We believe that the computed cardiovascular signatures have utility in monitoring cardiovascular health over time, including detecting abnormalities and quantifying recovery from acute events. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01696v1 |
| http://arxiv.org/pdf/1812.01696v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-individualized-cardiovascular |
| Repo | |
| Framework | |
Program Language Translation Using a Grammar-Driven Tree-to-Tree Model
| Title | Program Language Translation Using a Grammar-Driven Tree-to-Tree Model |
| Authors | Mehdi Drissi, Olivia Watkins, Aditya Khant, Vivaswat Ojha, Pedro Sandoval, Rakia Segev, Eric Weiner, Robert Keller |
| Abstract | The task of translating between programming languages differs from the challenge of translating natural languages in that programming languages are designed with a far more rigid set of structural and grammatical rules. Previous work has used a tree-to-tree encoder/decoder model to take advantage of the inherent tree structure of programs during translation. Neural decoders, however, by default do not exploit known grammar rules of the target language. In this paper, we describe a tree decoder that leverages knowledge of a language’s grammar rules to exclusively generate syntactically correct programs. We find that this grammar-based tree-to-tree model outperforms the state of the art tree-to-tree model in translating between two programming languages on a previously used synthetic task. |
| Tasks | |
| Published | 2018-07-04 |
| URL | http://arxiv.org/abs/1807.01784v1 |
| http://arxiv.org/pdf/1807.01784v1.pdf | |
| PWC | https://paperswithcode.com/paper/program-language-translation-using-a-grammar |
| Repo | |
| Framework | |
Learning to Reconstruct Texture-less Deformable Surfaces from a Single View
| Title | Learning to Reconstruct Texture-less Deformable Surfaces from a Single View |
| Authors | Jan Bednařík, Pascal Fua, Mathieu Salzmann |
| Abstract | Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, and essentially relates to Shape-from-Shading. In this paper, we introduce a data-driven approach to this problem. We introduce a general framework that can predict diverse 3D representations, such as meshes, normals, and depth maps. Our experiments show that meshes are ill-suited to handle texture-less 3D reconstruction in our context. Furthermore, we demonstrate that our approach generalizes well to unseen objects, and that it yields higher-quality reconstructions than a state-of-the-art SfS technique, particularly in terms of normal estimates. Our reconstructions accurately model the fine details of the surfaces, such as the creases of a T-Shirt worn by a person. |
| Tasks | 3D Reconstruction |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08908v2 |
| http://arxiv.org/pdf/1803.08908v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-reconstruct-texture-less |
| Repo | |
| Framework | |
Matlab Implementation of Machine Vision Algorithm on Ballast Degradation Evaluation
| Title | Matlab Implementation of Machine Vision Algorithm on Ballast Degradation Evaluation |
| Authors | Zixu Zhao |
| Abstract | America has a massive railway system. As of 2006, U.S. freight railroads have 140,490 route- miles of standard gauge, but maintaining such a huge system and eliminating any dangers, like reduced track stability and poor drainage, caused by railway ballast degradation require huge amount of labor. The traditional way to quantify the degradation of ballast is to use an index called Fouling Index (FI) through ballast sampling and sieve analysis. However, determining the FI values in lab is very time-consuming and laborious, but with the help of recent development in the field of computer vision, a novel method for a potential machine-vison based ballast inspection system can be employed that can hopefully replace the traditional mechanical method. The new machine-vision approach analyses the images of the in-service ballasts, and then utilizes image segmentation algorithm to get ballast segments. By comparing the segment results and their corresponding FI values, this novel method produces a machine-vision-based index that has the best-fit relation with FI. The implementation details of how this algorithm works are discussed in this report. |
| Tasks | Semantic Segmentation |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.08835v1 |
| http://arxiv.org/pdf/1804.08835v1.pdf | |
| PWC | https://paperswithcode.com/paper/matlab-implementation-of-machine-vision |
| Repo | |
| Framework | |
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
| Title | Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow |
| Authors | Xiao Zhang, Simon S. Du, Quanquan Gu |
| Abstract | We revisit the inductive matrix completion problem that aims to recover a rank-$r$ matrix with ambient dimension $d$ given $n$ features as the side prior information. The goal is to make use of the known $n$ features to reduce sample and computational complexities. We present and analyze a new gradient-based non-convex optimization algorithm that converges to the true underlying matrix at a linear rate with sample complexity only linearly depending on $n$ and logarithmically depending on $d$. To the best of our knowledge, all previous algorithms either have a quadratic dependency on the number of features in sample complexity or a sub-linear computational convergence rate. In addition, we provide experiments on both synthetic and real world data to demonstrate the effectiveness of our proposed algorithm. |
| Tasks | Matrix Completion |
| Published | 2018-03-03 |
| URL | http://arxiv.org/abs/1803.01233v1 |
| http://arxiv.org/pdf/1803.01233v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-sample-efficient-inductive-matrix |
| Repo | |
| Framework | |
