Paper Group ANR 649
Migration through Machine Learning Lens – Predicting Sexual and Reproductive Health Vulnerability of Young Migrants. JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English. A Quantum Computational Approach to Correspondence Problems on Point Sets. Detecting Local Insights from Global Labels: Supe …
Migration through Machine Learning Lens – Predicting Sexual and Reproductive Health Vulnerability of Young Migrants
| Title | Migration through Machine Learning Lens – Predicting Sexual and Reproductive Health Vulnerability of Young Migrants |
| Authors | Amber Nigam, Pragati Jaiswal, Uma Girkar, Teertha Arora, Leo A. Celi |
| Abstract | In this paper, we have discussed initial findings and results of our experiment to predict sexual and reproductive health vulnerabilities of migrants in a data-constrained environment. Notwithstanding the limited research and data about migrants and migration cities, we propose a solution that simultaneously focuses on data gathering from migrants, augmenting awareness of the migrants to reduce mishaps, and setting up a mechanism to present insights to the key stakeholders in migration to act upon. We have designed a webapp for the stakeholders involved in migration: migrants, who would participate in data gathering process and can also use the app for getting to know safety and awareness tips based on analysis of the data received; public health workers, who would have an access to the database of migrants on the app; policy makers, who would have a greater understanding of the ground reality, and of the patterns of migration through machine-learned analysis. Finally, we have experimented with different machine learning models on an artificially curated dataset. We have shown, through experiments, how machine learning can assist in predicting the migrants at risk and can also help in identifying the critical factors that make migration dangerous for migrants. The results for identifying vulnerable migrants through machine learning algorithms are statistically significant at an alpha of 0.05. |
| Tasks | |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02390v4 |
| https://arxiv.org/pdf/1910.02390v4.pdf | |
| PWC | https://paperswithcode.com/paper/migration-through-machine-learning-lens |
| Repo | |
| Framework | |
JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English
| Title | JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English |
| Authors | Sainik Kumar Mahata, Dipankar Das, Sivaji Bandyopadhyay |
| Abstract | In the current work, we present a description of the system submitted to WMT 2018 News Translation Shared task. The system was created to translate news text from Finnish to English. The system used a Character Based Neural Machine Translation model to accomplish the given task. The current paper documents the preprocessing steps, the description of the submitted system and the results produced using the same. Our system garnered a BLEU score of 12.9. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00323v1 |
| https://arxiv.org/pdf/1908.00323v1.pdf | |
| PWC | https://paperswithcode.com/paper/jucbnmt-at-wmt2018-news-translation-task-1 |
| Repo | |
| Framework | |
A Quantum Computational Approach to Correspondence Problems on Point Sets
| Title | A Quantum Computational Approach to Correspondence Problems on Point Sets |
| Authors | Vladislav Golyanik, Christian Theobalt |
| Abstract | Modern adiabatic quantum computers (AQC) are already used to solve difficult combinatorial optimisation problems in various domains of science. Currently, only a few applications of AQC in computer vision have been demonstrated. We review AQC and derive a new algorithm for correspondence problems on point sets suitable for execution on AQC. Our algorithm has a subquadratic computational complexity of the state preparation. Examples of successful transformation estimation and point set alignment by simulated sampling are shown in the systematic experimental evaluation. Finally, we analyse the differences in the solutions and the corresponding energy values. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.12296v2 |
| https://arxiv.org/pdf/1912.12296v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-quantum-computational-approach-to |
| Repo | |
| Framework | |
Detecting Local Insights from Global Labels: Supervised & Zero-Shot Sequence Labeling via a Convolutional Decomposition
| Title | Detecting Local Insights from Global Labels: Supervised & Zero-Shot Sequence Labeling via a Convolutional Decomposition |
| Authors | Allen Schmaltz |
| Abstract | Zero-shot grammatical error detection is the task of tagging token-level errors in a sentence when only given access to labels at the sentence-level for training. We present and analyze BLADE, a sequence labeling approach based on a decomposition of the filter-ngram interactions of a single-layer one-dimensional convolutional neural network as the final layer of a network, which has the characteristic of being effective in both the fully-supervised and zero-shot settings. The approach also enables a matching method, exemplar auditing, useful for analyzing the model and data, and empirically, as part of an inference-time decision rule. Additionally, we extend these insights from natural language to machine generated language, demonstrating that the strong sequence model can be used to guide synthetic text generation, and that it is concomitantly unsuitable as a reliable detector of synthetic data when the detection model and a sufficiently strong generation model are both accessible. We close with qualitative evidence that the approach can be a useful tool for preliminary text and document analysis, demonstrating that a strong text feature extractor for low- and high- resource settings is useful across NLP tasks. |
| Tasks | Grammatical Error Detection, Text Generation, Word Embeddings |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01154v4 |
| https://arxiv.org/pdf/1906.01154v4.pdf | |
| PWC | https://paperswithcode.com/paper/toward-grammatical-error-detection-from |
| Repo | |
| Framework | |
Mobile Artificial Intelligence Technology for Detecting Macula Edema and Subretinal Fluid on OCT Scans: Initial Results from the DATUM alpha Study
| Title | Mobile Artificial Intelligence Technology for Detecting Macula Edema and Subretinal Fluid on OCT Scans: Initial Results from the DATUM alpha Study |
| Authors | Stephen G. Odaibo, Mikelson MomPremier, Richard Y. Hwang, Salman J. Yousuf, Steven L. Williams, Joshua Grant |
| Abstract | Artificial Intelligence (AI) is necessary to address the large and growing deficit in retina and healthcare access globally. And mobile AI diagnostic platforms running in the Cloud may effectively and efficiently distribute such AI capability. Here we sought to evaluate the feasibility of Cloud-based mobile artificial intelligence for detection of retinal disease. And to evaluate the accuracy of a particular such system for detection of subretinal fluid (SRF) and macula edema (ME) on OCT scans. A multicenter retrospective image analysis was conducted in which board-certified ophthalmologists with fellowship training in retina evaluated OCT images of the macula. They noted the presence or absence of ME or SRF, then compared their assessment to that obtained from Fluid Intelligence, a mobile AI app that detects SRF and ME on OCT scans. Investigators consecutively selected retinal OCTs, while making effort to balance the number of scans with retinal fluid and scans without. Exclusion criteria included poor scan quality, ambiguous features, macula holes, retinoschisis, and dense epiretinal membranes. Accuracy in the form of sensitivity and specificity of the AI mobile App was determined by comparing its assessments to those of the retina specialists. At the time of this submission, five centers have completed their initial studies. This consists of a total of 283 OCT scans of which 155 had either ME or SRF (“wet”) and 128 did not (“dry”). The sensitivity ranged from 82.5% to 97% with a weighted average of 89.3%. The specificity ranged from 52% to 100% with a weighted average of 81.23%. CONCLUSION: Cloud-based Mobile AI technology is feasible for the detection retinal disease. In particular, Fluid Intelligence (alpha version), is sufficiently accurate as a screening tool for SRF and ME, especially in underserved areas. Further studies and technology development is needed. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.02905v2 |
| http://arxiv.org/pdf/1902.02905v2.pdf | |
| PWC | https://paperswithcode.com/paper/mobile-artificial-intelligence-technology-for |
| Repo | |
| Framework | |
1-point RANSAC for Circular Motion Estimation in Computed Tomography (CT)
| Title | 1-point RANSAC for Circular Motion Estimation in Computed Tomography (CT) |
| Authors | Mikhail O. Chekanov, Oleg S. Shipitko, Egor I. Ershov |
| Abstract | This paper proposes a RANSAC-based algorithm for determining the axial rotation angle of an object from a pair of its tomographic projections. An equation is derived for calculating the rotation angle using one correct keypoints correspondence of two tomographic projections. The proposed algorithm consists of the following steps: keypoints detection and matching, rotation angle estimation for each correspondence, outliers filtering with the RANSAC algorithm, finally, calculation of the desired angle by minimizing the re-projection error from the remaining correspondences. To validate the proposed method an experimental comparison against methods based on analysis of the distribution of the angles computed from all correspondences is conducted. |
| Tasks | Computed Tomography (CT), Motion Estimation |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01681v1 |
| https://arxiv.org/pdf/1910.01681v1.pdf | |
| PWC | https://paperswithcode.com/paper/1-point-ransac-for-circular-motion-estimation |
| Repo | |
| Framework | |
Inverses of Matern Covariances on Grids
| Title | Inverses of Matern Covariances on Grids |
| Authors | Joseph Guinness |
| Abstract | We conduct a theoretical and numerical study of the aliased spectral densities and inverse operators of Mat'ern covariance functions on regular grids. We apply our results to provide clarity on the properties of a popular approximation based on stochastic partial differential equations; we find that it can approximate the aliased spectral density and the covariance operator well as the grid spacing goes to zero, but it does not provide increasingly accurate approximations to the inverse operator as the grid spacing goes to zero. If a sparse approximation to the inverse is desired, we suggest instead to select a KL-divergence-minimizing sparse approximation and demonstrate in simulations that these sparse approximations deliver accurate Mat'ern parameter estimates, while the SPDE approximation over-estimates spatial dependence. |
| Tasks | |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11914v1 |
| https://arxiv.org/pdf/1912.11914v1.pdf | |
| PWC | https://paperswithcode.com/paper/inverses-of-matern-covariances-on-grids |
| Repo | |
| Framework | |
Preserving Patient Privacy while Training a Predictive Model of In-hospital Mortality
| Title | Preserving Patient Privacy while Training a Predictive Model of In-hospital Mortality |
| Authors | Pulkit Sharma, Farah E Shamout, David A Clifton |
| Abstract | Machine learning models can be used for pattern recognition in medical data in order to improve patient outcomes, such as the prediction of in-hospital mortality. Deep learning models, in particular, require large amounts of data for model training. However, the data is often collected at different hospitals and sharing is restricted due to patient privacy concerns. In this paper, we aimed to demonstrate the potential of distributed training in achieving state-of-the-art performance while maintaining data privacy. Our results show that training the model in the federated learning framework leads to comparable performance to the traditional centralised setting. We also suggest several considerations for the success of such frameworks in future work. |
| Tasks | |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.00354v1 |
| https://arxiv.org/pdf/1912.00354v1.pdf | |
| PWC | https://paperswithcode.com/paper/preserving-patient-privacy-while-training-a |
| Repo | |
| Framework | |
Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection
| Title | Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection |
| Authors | Masahiro Kaneko, Mamoru Komachi |
| Abstract | It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary, and simply using the output of the final layer is not necessarily sufficient. Moreover, to our knowledge, exploiting large language representation models to detect grammatical errors has not yet been studied. In this work, we investigate the effect of utilizing information not only from the final layer but also from intermediate layers of a pre-trained language representation model to detect grammatical errors. We propose a multi-head multi-layer attention model that determines the appropriate layers in Bidirectional Encoder Representation from Transformers (BERT). The proposed method achieved the best scores on three datasets for grammatical error detection tasks, outperforming the current state-of-the-art method by 6.0 points on FCE, 8.2 points on CoNLL14, and 12.2 points on JFLEG in terms of F_0.5. We also demonstrate that by using multi-head multi-layer attention, our model can exploit a broader range of information for each token in a sentence than a model that uses only the final layer’s information. |
| Tasks | Grammatical Error Detection |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07334v1 |
| http://arxiv.org/pdf/1904.07334v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-head-multi-layer-attention-to-deep |
| Repo | |
| Framework | |
On Convergence Rate of the Gaussian Belief Propagation Algorithm for Markov Networks
| Title | On Convergence Rate of the Gaussian Belief Propagation Algorithm for Markov Networks |
| Authors | Zhaorong Zhang, Minyue Fu |
| Abstract | Gaussian Belief Propagation (BP) algorithm is one of the most important distributed algorithms in signal processing and statistical learning involving Markov networks. It is well known that the algorithm correctly computes marginal density functions from a high dimensional joint density function over a Markov network in a finite number of iterations when the underlying Gaussian graph is acyclic. It is also known more recently that the algorithm produces correct marginal means asymptotically for cyclic Gaussian graphs under the condition of walk summability. This paper extends this convergence result further by showing that the convergence is exponential under the walk summability condition, and provides a simple bound for the convergence rate. |
| Tasks | |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02658v1 |
| http://arxiv.org/pdf/1903.02658v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-convergence-rate-of-the-gaussian-belief |
| Repo | |
| Framework | |
Richness of Deep Echo State Network Dynamics
| Title | Richness of Deep Echo State Network Dynamics |
| Authors | Claudio Gallicchio, Alessio Micheli |
| Abstract | Reservoir Computing (RC) is a popular methodology for the efficient design of Recurrent Neural Networks (RNNs). Recently, the advantages of the RC approach have been extended to the context of multi-layered RNNs, with the introduction of the Deep Echo State Network (DeepESN) model. In this paper, we study the quality of state dynamics in progressively higher layers of DeepESNs, using tools from the areas of information theory and numerical analysis. Our experimental results on RC benchmark datasets reveal the fundamental role played by the strength of inter-reservoir connections to increasingly enrich the representations developed in higher layers. Our analysis also gives interesting insights into the possibility of effective exploitation of training algorithms based on stochastic gradient descent in the RC field. |
| Tasks | |
| Published | 2019-03-12 |
| URL | https://arxiv.org/abs/1903.05174v2 |
| https://arxiv.org/pdf/1903.05174v2.pdf | |
| PWC | https://paperswithcode.com/paper/richness-of-deep-echo-state-network-dynamics |
| Repo | |
| Framework | |
Planning Robot Motion using Deep Visual Prediction
| Title | Planning Robot Motion using Deep Visual Prediction |
| Authors | Meenakshi Sarkar, Prabhu Pradhan, Debasish Ghose |
| Abstract | In this paper, we introduce a novel framework that can learn to make visual predictions about the motion of a robotic agent from raw video frames. Our proposed motion prediction network (PROM-Net) can learn in a completely unsupervised manner and efficiently predict up to 10 frames in the future. Moreover, unlike any other motion prediction models, it is lightweight and once trained it can be easily implemented on mobile platforms that have very limited computing capabilities. We have created a new robotic data set comprising LEGO Mindstorms moving along various trajectories in three different environments under different lighting conditions for testing and training the network. Finally, we introduce a framework that would use the predicted frames from the network as an input to a model predictive controller for motion planning in unknown dynamic environments with moving obstacles. |
| Tasks | Motion Planning, motion prediction |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10182v1 |
| https://arxiv.org/pdf/1906.10182v1.pdf | |
| PWC | https://paperswithcode.com/paper/planning-robot-motion-using-deep-visual |
| Repo | |
| Framework | |
Analysis of Memory Capacity for Deep Echo State Networks
| Title | Analysis of Memory Capacity for Deep Echo State Networks |
| Authors | Xuanlin Liu, Mingzhe Chen, Changchuan Yin, Walid Saad |
| Abstract | In this paper, the echo state network (ESN) memory capacity, which represents the amount of input data an ESN can store, is analyzed for a new type of deep ESNs. In particular, two deep ESN architectures are studied. First, a parallel deep ESN is proposed in which multiple reservoirs are connected in parallel allowing them to average outputs of multiple ESNs, thus decreasing the prediction error. Then, a series architecture ESN is proposed in which ESN reservoirs are placed in cascade that the output of each ESN is the input of the next ESN in the series. This series ESN architecture can capture more features between the input sequence and the output sequence thus improving the overall prediction accuracy. Fundamental analysis shows that the memory capacity of parallel ESNs is equivalent to that of a traditional shallow ESN, while the memory capacity of series ESNs is smaller than that of a traditional shallow ESN.In terms of normalized root mean square error, simulation results show that the parallel deep ESN achieves 38.5% reduction compared to the traditional shallow ESN while the series deep ESN achieves 16.8% reduction. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1908.07063v1 |
| https://arxiv.org/pdf/1908.07063v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-memory-capacity-for-deep-echo |
| Repo | |
| Framework | |
Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks
| Title | Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks |
| Authors | Florian Dubost, Hieab Adams, Pinar Yilmaz, Gerda Bortsova, Gijs van Tulder, M. Arfan Ikram, Wiro Niessen, Meike Vernooij, Marleen de Bruijne |
| Abstract | Finding automatically multiple lesions in large images is a common problem in medical image analysis. Solving this problem can be challenging if, during optimization, the automated method cannot access information about the location of the lesions nor is given single examples of the lesions. We propose a new weakly supervised detection method using neural networks, that computes attention maps revealing the locations of brain lesions. These attention maps are computed using the last feature maps of a segmentation network optimized only with global image-level labels. The proposed method can generate attention maps at full input resolution without need for interpolation during preprocessing, which allows small lesions to appear in attention maps. For comparison, we modify state-of-the-art methods to compute attention maps for weakly supervised object detection, by using a global regression objective instead of the more conventional classification objective. This regression objective optimizes the number of occurrences of the target object in an image, e.g. the number of brain lesions in a scan, or the number of digits in an image. We study the behavior of the proposed method in MNIST-based detection datasets, and evaluate it for the challenging detection of enlarged perivascular spaces - a type of brain lesion - in a dataset of 2202 3D scans with point-wise annotations in the center of all lesions in four brain regions. In the brain dataset, the weakly supervised detection methods come close to the human intrarater agreement in each region. The proposed method reaches the best area under the curve in two out of four regions, and has the lowest number of false positive detections in all regions, while its average sensitivity over all regions is similar to that of the other best methods. The proposed method can facilitate epidemiological and clinical studies of enlarged perivascular spaces. |
| Tasks | Object Detection, Weakly Supervised Object Detection |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01891v4 |
| https://arxiv.org/pdf/1906.01891v4.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-object-detection-with-2d |
| Repo | |
| Framework | |
A Logical Model for Supporting Social Commonsense Knowledge Acquisition
| Title | A Logical Model for Supporting Social Commonsense Knowledge Acquisition |
| Authors | Zhenzhen Gu, Cungen Cao, Ya Wang, Yuefei Sui |
| Abstract | To make machine exhibit human-like abilities in the domains like robotics and conversation, social commonsense knowledge (SCK), i.e., common sense about social contexts and social roles, is absolutely necessarily. Therefor, our ultimate goal is to acquire large-scale SCK to support much more intelligent applications. Before that, we need to know clearly what is SCK and how to represent it, since automatic information processing requires data and knowledge are organized in structured and semantically related ways. For this reason, in this paper, we identify and formalize three basic types of SCK based on first-order theory. Firstly, we identify and formalize the interrelationships, such as having-role and having-social_relation, among social contexts, roles and players from the perspective of considering both contexts and roles as first-order citizens and not generating role instances. Secondly, we provide a four level structure to identify and formalize the intrinsic information, such as events and desires, of social contexts, roles and players, and illustrate the way of harvesting the intrinsic information of social contexts and roles from the exhibition of players in concrete contexts. And thirdly, enlightened by some observations of actual contexts, we further introduce and formalize the embedding of social contexts, and depict the way of excavating the intrinsic information of social contexts and roles from the embedded smaller and simpler contexts. The results of this paper lay the foundation not only for formalizing much more complex SCK but also for acquiring these three basic types of SCK. |
| Tasks | Common Sense Reasoning |
| Published | 2019-12-25 |
| URL | https://arxiv.org/abs/1912.11599v1 |
| https://arxiv.org/pdf/1912.11599v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-logical-model-for-supporting-social |
| Repo | |
| Framework | |
