Paper Group ANR 465
Validation of a recommender system for prompting omitted foods in online dietary assessment surveys. A Collaborative Ecosystem for Digital Coptic Studies. Infant brain MRI segmentation with dilated convolution pyramid downsampling and self-attention. Privacy Preserving Off-Policy Evaluation. Generating Synthetic Audio Data for Attention-Based Speec …
Validation of a recommender system for prompting omitted foods in online dietary assessment surveys
| Title | Validation of a recommender system for prompting omitted foods in online dietary assessment surveys |
| Authors | Timur Osadchiy, Ivan Poliakov, Patrick Olivier, Maisie Rowland, Emma Foster |
| Abstract | Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment. We evaluated the effectiveness of a recommender algorithm developed for an online dietary assessment system called Intake24, that automates the multiple-pass 24-hour recall method. The recommender builds a model of eating behavior from recalls collected in past surveys. Based on foods they have already selected, the model is used to remind respondents of associated foods that they may have omitted to report. The performance of prompts generated by the model was compared to that of prompts hand-coded by nutritionists in two dietary studies. The results of our studies demonstrate that the recommender system is able to capture a higher number of foods omitted by respondents of online dietary surveys than prompts hand-coded by nutritionists. However, the considerably lower precision of generated prompts indicates an opportunity for further improvement of the system. |
| Tasks | Recommendation Systems |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.12264v1 |
| http://arxiv.org/pdf/1903.12264v1.pdf | |
| PWC | https://paperswithcode.com/paper/validation-of-a-recommender-system-for |
| Repo | |
| Framework | |
A Collaborative Ecosystem for Digital Coptic Studies
| Title | A Collaborative Ecosystem for Digital Coptic Studies |
| Authors | Caroline T. Schroeder, Amir Zeldes |
| Abstract | Scholarship on underresourced languages bring with them a variety of challenges which make access to the full spectrum of source materials and their evaluation difficult. For Coptic in particular, large scale analyses and any kind of quantitative work become difficult due to the fragmentation of manuscripts, the highly fusional nature of an incorporational morphology, and the complications of dealing with influences from Hellenistic era Greek, among other concerns. Many of these challenges, however, can be addressed using Digital Humanities tools and standards. In this paper, we outline some of the latest developments in Coptic Scriptorium, a DH project dedicated to bringing Coptic resources online in uniform, machine readable, and openly available formats. Collaborative web-based tools create online ‘virtual departments’ in which scholars dispersed sparsely across the globe can collaborate, and natural language processing tools counterbalance the scarcity of trained editors by enabling machine processing of Coptic text to produce searchable, annotated corpora. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05082v1 |
| https://arxiv.org/pdf/1912.05082v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-collaborative-ecosystem-for-digital-coptic |
| Repo | |
| Framework | |
Infant brain MRI segmentation with dilated convolution pyramid downsampling and self-attention
| Title | Infant brain MRI segmentation with dilated convolution pyramid downsampling and self-attention |
| Authors | Zhihao Lei, Lin Qi, Ying Wei, Yunlong Zhou |
| Abstract | In this paper, we propose a dual aggregation network to adaptively aggregate different information in infant brain MRI segmentation. More precisely, we added two modules based on 3D-UNet to better model information at different levels and locations. The dilated convolution pyramid downsampling module is mainly to solve the problem of loss of spatial information on the downsampling process, and it can effectively save details while reducing the resolution. The self-attention module can integrate the remote dependence on the feature maps in two dimensions of spatial and channel, effectively improving the representation ability and discriminating ability of the model. Our results are compared to the winners of iseg2017’s first evaluation, the DICE ratio of WM and GM increased by 0.7%, and CSF is comparable.In the latest evaluation of the iseg-2019 cross-dataset challenge,we achieve the first place in the DICE of WM and GM, and the DICE of CSF is second. |
| Tasks | Infant Brain Mri Segmentation |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/1912.12570v2 |
| https://arxiv.org/pdf/1912.12570v2.pdf | |
| PWC | https://paperswithcode.com/paper/infant-brain-mri-segmentation-with-dilated |
| Repo | |
| Framework | |
Privacy Preserving Off-Policy Evaluation
| Title | Privacy Preserving Off-Policy Evaluation |
| Authors | Tengyang Xie, Philip S. Thomas, Gerome Miklau |
| Abstract | Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, we present the first differentially private approach for off-policy evaluation. We provide a theoretical analysis of the privacy-preserving properties of our algorithm and analyze its utility (speed of convergence). After describing some results of this theoretical analysis, we show empirically that our method outperforms previous methods (which are restricted to the on-policy setting). |
| Tasks | |
| Published | 2019-02-01 |
| URL | http://arxiv.org/abs/1902.00174v1 |
| http://arxiv.org/pdf/1902.00174v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-off-policy-evaluation |
| Repo | |
| Framework | |
Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems
| Title | Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems |
| Authors | Nick Rossenbach, Albert Zeyer, Ralf Schlüter, Hermann Ney |
| Abstract | Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS system trained only on the ASR corpora itself. ASR and TTS systems are built separately to show that text-only data can be used to enhance existing end-to-end ASR systems without the necessity of parameter or architecture changes. We compare our method with language model integration of the same text data and with simple data augmentation methods like SpecAugment and show that performance improvements are mostly independent. We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50%. We also show improvements of up to 5% relative WER over our most recent ASR baseline on LibriSpeech-960h. |
| Tasks | Data Augmentation, End-To-End Speech Recognition, Language Modelling, Speech Recognition |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09257v2 |
| https://arxiv.org/pdf/1912.09257v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-synthetic-audio-data-for-attention |
| Repo | |
| Framework | |
Data-driven model for fracturing design optimization: focus on building digital database and production forecast
| Title | Data-driven model for fracturing design optimization: focus on building digital database and production forecast |
| Authors | A. D. Morozov, D. O. Popkov, V. M. Duplyakov, R. F. Mutalova, A. A. Osiptsov, A. L. Vainshtein, E. V. Burnaev, E. V. Shel, G. V. Paderin |
| Abstract | Growing amount of hydraulic fracturing (HF) jobs in the recent two decades resulted in a significant amount of measured data available for construction of predictive models via machine learning (ML). There is a significant room for fracturing design optimization. We propose a data-driven model for fracturing design optimization, where the workflow is essentially split into two stages. As a result of the first stage, the present paper summarizes the efforts into the creation of a digital database of field data from several thousands of multistage HF jobs on vertical, inclined and near-horizontal wells from about twenty different oilfields in Western Siberia, Russia. In terms of the number of points (fracturing jobs), the present database is a rare case of a representative dataset of about 6000 of data points, compared to typical databases available in the literature, comprising tens or hundreds of points at best. Each point in the data base is based on the vector of 92 input variables (the reservoir, well and the frac design parameters). Production data is characterized by 16 parameters, including the target, cumulative oil production. The focus is made on data gathering from various sources, data preprocessing and development of the architecture of a database as well as solving the production forecast problem via ML. Data preparation has been done using various ML techniques: the problem of missing values in the database is solved with collaborative filtering for data imputation; outliers are removed using visualisation of cluster data structure by t-SNE algorithm. The production forecast problem is solved via CatBoost algorithm. |
| Tasks | Imputation |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.14499v2 |
| https://arxiv.org/pdf/1910.14499v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-on-field-data-for-hydraulic |
| Repo | |
| Framework | |
“The Human Body is a Black Box”: Supporting Clinical Decision-Making with Deep Learning
| Title | “The Human Body is a Black Box”: Supporting Clinical Decision-Making with Deep Learning |
| Authors | Mark Sendak, Madeleine Elish, Michael Gao, Joseph Futoma, William Ratliff, Marshall Nichols, Armando Bedoya, Suresh Balu, Cara O’Brien |
| Abstract | Machine learning technologies are increasingly developed for use in healthcare. While research communities have focused on creating state-of-the-art models, there has been less focus on real world implementation and the associated challenges to accuracy, fairness, accountability, and transparency that come from actual, situated use. Serious questions remain under examined regarding how to ethically build models, interpret and explain model output, recognize and account for biases, and minimize disruptions to professional expertise and work cultures. We address this gap in the literature and provide a detailed case study covering the development, implementation, and evaluation of Sepsis Watch, a machine learning-driven tool that assists hospital clinicians in the early diagnosis and treatment of sepsis. We, the team that developed and evaluated the tool, discuss our conceptualization of the tool not as a model deployed in the world but instead as a socio-technical system requiring integration into existing social and professional contexts. Rather than focusing on model interpretability to ensure a fair and accountable machine learning, we point toward four key values and practices that should be considered when developing machine learning to support clinical decision-making: rigorously define the problem in context, build relationships with stakeholders, respect professional discretion, and create ongoing feedback loops with stakeholders. Our work has significant implications for future research regarding mechanisms of institutional accountability and considerations for designing machine learning systems. Our work underscores the limits of model interpretability as a solution to ensure transparency, accuracy, and accountability in practice. Instead, our work demonstrates other means and goals to achieve FATML values in design and in practice. |
| Tasks | Decision Making |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08089v2 |
| https://arxiv.org/pdf/1911.08089v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-human-body-is-a-black-box-supporting |
| Repo | |
| Framework | |
Detecting and Reducing Bias in a High Stakes Domain
| Title | Detecting and Reducing Bias in a High Stakes Domain |
| Authors | Ruiqi Zhong, Yanda Chen, Desmond Patton, Charlotte Selous, Kathy McKeown |
| Abstract | Gang-involved youth in cities such as Chicago sometimes post on social media to express their aggression towards rival gangs and previous research has demonstrated that a deep learning approach can predict aggression and loss in posts. To address the possibility of bias in this sensitive application, we developed an approach to systematically interpret the state of the art model. We found, surprisingly, that it frequently bases its predictions on stop words such as “a” or “on”, an approach that could harm social media users who have no aggressive intentions. To tackle this bias, domain experts annotated the rationales, highlighting words that explain why a tweet is labeled as “aggression”. These new annotations enable us to quantitatively measure how justified the model predictions are, and build models that drastically reduce bias. Our study shows that in high stake scenarios, accuracy alone cannot guarantee a good system and we need new evaluation methods. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11474v2 |
| https://arxiv.org/pdf/1908.11474v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-and-reducing-bias-in-a-high-stakes |
| Repo | |
| Framework | |
Learning Fair and Transferable Representations
| Title | Learning Fair and Transferable Representations |
| Authors | Luca Oneto, Michele Donini, Andreas Maurer, Massimiliano Pontil |
| Abstract | Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints. In this work we measure fairness according to demographic parity. This requires the probability of the possible model decisions to be independent of the sensitive information. We argue that the goal of imposing demographic parity can be substantially facilitated within a multitask learning setting. We leverage task similarities by encouraging a shared fair representation across the tasks via low rank matrix factorization. We derive learning bounds establishing that the learned representation transfers well to novel tasks both in terms of prediction performance and fairness metrics. We present experiments on three real world datasets, showing that the proposed method outperforms state-of-the-art approaches by a significant margin. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10673v3 |
| https://arxiv.org/pdf/1906.10673v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-fair-and-transferable |
| Repo | |
| Framework | |
Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields
| Title | Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields |
| Authors | Leixin Zhou, Zisha Zhong, Abhay Shah, Bensheng Qiu, John Buatti, Xiaodong Wu |
| Abstract | Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach (e.g., U-net), which predicts the probability of being target object or background for each voxel. One problem of those methods is lacking of topology guarantee for segmented objects, and usually post processing is needed to infer the boundary surface of the object. In this paper, a novel model based on 3-D convolutional neural networks (CNNs) and Conditional Random Fields (CRFs) is proposed to tackle the surface segmentation problem with end-to-end training. To the best of our knowledge, this is the first study to apply a 3-D neural network with a CRFs model for direct surface segmentation. Experiments carried out on NCI-ISBI 2013 MR prostate dataset and Medical Segmentation Decathlon Spleen dataset demonstrated promising segmentation results. |
| Tasks | Semantic Segmentation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04714v2 |
| https://arxiv.org/pdf/1906.04714v2.pdf | |
| PWC | https://paperswithcode.com/paper/3-d-surface-segmentation-meets-conditional |
| Repo | |
| Framework | |
Automatic Defect Segmentation on Leather with Deep Learning
| Title | Automatic Defect Segmentation on Leather with Deep Learning |
| Authors | Sze-Teng Liong, Y. S. Gan, Yen-Chang Huang, Chang-Ann Yuan, Hsiu-Chi Chang |
| Abstract | Leather is a natural and durable material created through a process of tanning of hides and skins of animals. The price of the leather is subjective as it is highly sensitive to its quality and surface defects condition. In the literature, there are very few works investigating on the defects detection for leather using automatic image processing techniques. The manual defect inspection process is essential in an leather production industry to control the quality of the finished products. However, it is tedious, as it is labour intensive, time consuming, causes eye fatigue and often prone to human error. In this paper, a fully automatic defect detection and marking system on a calf leather is proposed. The proposed system consists of a piece of leather, LED light, high resolution camera and a robot arm. Succinctly, a machine vision method is presented to identify the position of the defects on the leather using a deep learning architecture. Then, a series of processes are conducted to predict the defect instances, including elicitation of the leather images with a robot arm, train and test the images using a deep learning architecture and determination of the boundary of the defects using mathematical derivation of the geometry. Note that, all the processes do not involve human intervention, except for the defect ground truths construction stage. The proposed algorithm is capable to exhibit 91.5% segmentation accuracy on the train data and 70.35% on the test data. We also report confusion matrix, F1-score, precision and specificity, sensitivity performance metrics to further verify the effectiveness of the proposed approach. |
| Tasks | |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.12139v1 |
| http://arxiv.org/pdf/1903.12139v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-defect-segmentation-on-leather-with |
| Repo | |
| Framework | |
Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
| Title | Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback |
| Authors | Xiangyi Li, Huaming Wu |
| Abstract | In multiple-input multiple-output (MIMO) systems, it is crucial of utilizing the available channel state information (CSI) at the transmitter for precoding to improve the performance of frequency division duplex (FDD) networks. One of the mainchallenges is to compress a large amount of CSI in CSI feedback transmission in massive MIMO systems. In this paper, we propose a deep learning (DL)-based approach that uses a deep recurrent neural network (RNN) to learn temporal correlation and adopts depthwise separable convolution to shrink the model. The feature extraction module is also elaborately devised by studyingdecoupled spatio-temporal feature representations in different structures. Experimental results demonstrate that the proposed approach outperforms existing DL-based methods in terms of recovery quality and accuracy, which can also achieve remarkable robustness at low compression ratio (CR). |
| Tasks | |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.07934v2 |
| https://arxiv.org/pdf/1908.07934v2.pdf | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-representation-with-deep |
| Repo | |
| Framework | |
End-to-End Defect Detection in Automated Fiber Placement Based on Artificially Generated Data
| Title | End-to-End Defect Detection in Automated Fiber Placement Based on Artificially Generated Data |
| Authors | Sebastian Zambal, Christoph Heindl, Christian Eitzinger, Josef Scharinger |
| Abstract | Automated fiber placement (AFP) is an advanced manufacturing technology that increases the rate of production of composite materials. At the same time, the need for adaptable and fast inline control methods of such parts raises. Existing inspection systems make use of handcrafted filter chains and feature detectors, tuned for a specific measurement methods by domain experts. These methods hardly scale to new defects or different measurement devices. In this paper, we propose to formulate AFP defect detection as an image segmentation problem that can be solved in an end-to-end fashion using artificially generated training data. We employ a probabilistic graphical model to generate training images and annotations. We then train a deep neural network based on recent architectures designed for image segmentation. This leads to an appealing method that scales well with new defect types and measurement devices and requires little real world data for training. |
| Tasks | Semantic Segmentation |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04997v1 |
| https://arxiv.org/pdf/1910.04997v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-defect-detection-in-automated |
| Repo | |
| Framework | |
Variational Inference to Measure Model Uncertainty in Deep Neural Networks
| Title | Variational Inference to Measure Model Uncertainty in Deep Neural Networks |
| Authors | Konstantin Posch, Jan Steinbrener, Jürgen Pilz |
| Abstract | We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic. First, model uncertainty cannot be measured thus limiting the use of deep learning in many fields of application and second, training of deep neural networks is often hampered by overfitting. The proposed approach uses variational inference to approximate the intractable a posteriori distribution on basis of a normal prior. The variational density is designed in such a way that the a posteriori uncertainty of the network parameters is represented per network layer and depending on the estimated parameter expectation values. This way, only a few additional parameters need to be optimized compared to a non-Bayesian network. We apply this Bayesian approach to train and test the LeNet architecture on the MNIST dataset. Compared to classical deep learning, the test error is reduced by 15%. In addition, the trained model contains information about the parameter uncertainty in each layer. We show that this information can be used to calculate credible intervals for the prediction and to optimize the network architecture for a given training data set. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.10189v2 |
| http://arxiv.org/pdf/1902.10189v2.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-to-measure-model |
| Repo | |
| Framework | |
Distributed stochastic optimization with gradient tracking over strongly-connected networks
| Title | Distributed stochastic optimization with gradient tracking over strongly-connected networks |
| Authors | Ran Xin, Anit Kumar Sahu, Usman A. Khan, Soummya Kar |
| Abstract | In this paper, we study distributed stochastic optimization to minimize a sum of smooth and strongly-convex local cost functions over a network of agents, communicating over a strongly-connected graph. Assuming that each agent has access to a stochastic first-order oracle ($\mathcal{SFO}$), we propose a novel distributed method, called $\mathcal{S}$-$\mathcal{AB}$, where each agent uses an auxiliary variable to asymptotically track the gradient of the global cost in expectation. The $\mathcal{S}$-$\mathcal{AB}$ algorithm employs row- and column-stochastic weights simultaneously to ensure both consensus and optimality. Since doubly-stochastic weights are not used, $\mathcal{S}$-$\mathcal{AB}$ is applicable to arbitrary strongly-connected graphs. We show that under a sufficiently small constant step-size, $\mathcal{S}$-$\mathcal{AB}$ converges linearly (in expected mean-square sense) to a neighborhood of the global minimizer. We present numerical simulations based on real-world data sets to illustrate the theoretical results. |
| Tasks | Stochastic Optimization |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07266v2 |
| http://arxiv.org/pdf/1903.07266v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-stochastic-optimization-with |
| Repo | |
| Framework | |
