January 25, 2020

3264 words 16 mins read

Paper Group ANR 1665

Active learning for enumerating local minima based on Gaussian process derivatives. Modeling Electromagnetic Navigation Systems for Medical Applications using Random Forests and Artificial Neural Networks. Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors. Report on the SIGIR 2019 Workshop on eCommerce (ECOM19). BasisConv: A …

Active learning for enumerating local minima based on Gaussian process derivatives


Title	Active learning for enumerating local minima based on Gaussian process derivatives
Authors	Yu Inatsu, Daisuke Sugita, Kazuaki Toyoura, Ichiro Takeuchi
Abstract	We study active learning (AL) based on Gaussian Processes (GPs) for efficiently enumerating all of the local minimum solutions of a black-box function. This problem is challenging due to the fact that local solutions are characterized by their zero gradient and positive-definite Hessian properties, but those derivatives cannot be directly observed. We propose a new AL method in which the input points are sequentially selected such that the confidence intervals of the GP derivatives are effectively updated for enumerating local minimum solutions. We theoretically analyze the proposed method and demonstrate its usefulness through numerical experiments.
Tasks	Active Learning, Gaussian Processes
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03279v1
PDF	http://arxiv.org/pdf/1903.03279v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-enumerating-local-minima
Repo
Framework


Title	Modeling Electromagnetic Navigation Systems for Medical Applications using Random Forests and Artificial Neural Networks
Authors	Ruoxi Yu, Samuel L. Charreyron, Quentin Boehler, Cameron Weibel, Carmen C. Y. Poon, Bradley J. Nelson
Abstract	Electromagnetic Navigation Systems (eMNS) can be used to control a variety of multiscale devices within the human body for remote surgery. Accurate modeling of the magnetic fields generated by the electromagnets of an eMNS is crucial for the precise control of these devices. Existing methods assume a linear behavior of these systems, leading to significant modeling errors within nonlinear regions exhibited at higher magnetic fields. In this paper, we use a random forest (RF) and an artificial neural network (ANN) to model the nonlinear behavior of the magnetic fields generated by an eMNS. Both machine learning methods outperformed the state-of-the-art linear multipole electromagnet method (LMEM). The RF and the ANN model reduced the root mean squared error of the LMEM when predicting the field magnitude by around 40% and 80%, respectively, over the entire current range of the eMNS. At high current regions, especially between 30 and 35 A, the field-magnitude RMSE improvement of the ANN model over the LMEM was over 35 mT. This study demonstrates the feasibility of using machine learning methods to model an eMNS for medical applications, and its ability to account for complex nonlinear behavior at high currents. The use of machine learning thus shows promise for improving surgical procedures that use magnetic navigation.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12028v1
PDF	https://arxiv.org/pdf/1909.12028v1.pdf
PWC	https://paperswithcode.com/paper/modeling-electromagnetic-navigation-systems
Repo
Framework

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors


Title	Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
Authors	Gauri Jagatap, Chinmay Hegde
Abstract	Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned generative priors they do not require any training over large datasets. However, few theoretical guarantees exist in the scope of using untrained neural network priors for inverse imaging problems. We explore new applications and theory for untrained neural network priors. Specifically, we consider the problem of solving linear inverse problems, such as compressive sensing, as well as non-linear problems, such as compressive phase retrieval. We model images to lie in the range of an untrained deep generative network with a fixed seed. We further present a projected gradient descent scheme that can be used for both compressive sensing and phase retrieval and provide rigorous theoretical guarantees for its convergence. We also show both theoretically as well as empirically that with deep network priors, one can achieve better compression rates for the same image quality compared to hand crafted priors.
Tasks	Compressive Sensing, Denoising, Super-Resolution
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08763v2
PDF	https://arxiv.org/pdf/1906.08763v2.pdf
PWC	https://paperswithcode.com/paper/algorithmic-guarantees-for-inverse-imaging
Repo
Framework

Report on the SIGIR 2019 Workshop on eCommerce (ECOM19)


Title	Report on the SIGIR 2019 Workshop on eCommerce (ECOM19)
Authors	Jon Degenhardt, Surya Kallumadi, Utkarsh Porwal, Andrew Trotman
Abstract	The SIGIR 2019 Workshop on eCommerce (ECOM19), was a full day workshop that took place on Thursday, July 25, 2019 in Paris, France. The purpose of the workshop was to serve as a platform for publication and discussion of Information Retrieval and NLP research and their applications in the domain of eCommerce. The workshop program was designed to bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to product search and recommendation in the eCommerce domain. A second goal was to run a data challenge on real-world eCommerce data. The workshop drew contributions from both industry as well as academia, in total the workshop received 38 submissions, and accepted 24 (63%). There were two keynotes by invited speakers, a poster session where all the accepted submissions were presented, a panel discussion, and three short talks by invited speakers.
Tasks	Information Retrieval
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12282v1
PDF	https://arxiv.org/pdf/1912.12282v1.pdf
PWC	https://paperswithcode.com/paper/report-on-the-sigir-2019-workshop-on
Repo
Framework

BasisConv: A method for compressed representation and learning in CNNs


Title	BasisConv: A method for compressed representation and learning in CNNs
Authors	Muhammad Tayyab, Abhijit Mahalanobis
Abstract	It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights, filter quantization and representing filters in terms of a basis functions. Our approach falls in this latter class of strategies, but is distinct in that that we show both compressed learning and representation can be achieved without significant modifications of popular CNN architectures. Specifically, any convolution layer of the CNN is easily replaced by two successive convolution layers: the first is a set of fixed filters (that represent the knowledge space of the entire layer and do not change), which is followed by a layer of one-dimensional filters (that represent the learned knowledge in this space). For the pre-trained networks, the fixed layer is just the truncated eigen-decompositions of the original filters. The 1D filters are initialized as the weights of linear combination, but are fine-tuned to recover any performance loss due to the truncation. For training networks from scratch, we use a set of random orthogonal fixed filters (that never change), and learn the 1D weight vector directly from the labeled data. Our method substantially reduces i) the number of learnable parameters during training, and ii) the number of multiplication operations and filter storage requirements during implementation. It does so without requiring any special operators in the convolution layer, and extends to all known popular CNN architectures. We apply our method to four well known network architectures trained with three different data sets. Results show a consistent reduction in i) the number of operations by up to a factor of 5, and ii) number of learnable parameters by up to a factor of 18, with less than 3% drop in performance on the CIFAR100 dataset.
Tasks	Quantization
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04509v1
PDF	https://arxiv.org/pdf/1906.04509v1.pdf
PWC	https://paperswithcode.com/paper/basisconv-a-method-for-compressed
Repo
Framework

V2X System Architecture Utilizing Hybrid Gaussian Process-based Model Structures


Title	V2X System Architecture Utilizing Hybrid Gaussian Process-based Model Structures
Authors	Hossein Nourkhiz Mahjoub, Behrad Toghi, S M Osman Gani, Yaser P. Fallah
Abstract	Scalable communication is of utmost importance for reliable dissemination of time-sensitive information in cooperative vehicular ad-hoc networks (VANETs), which is, in turn, an essential prerequisite for the proper operation of the critical cooperative safety applications. The model-based communication (MBC) is a recently-explored scalability solution proposed in the literature, which has shown a promising potential to reduce the channel congestion to a great extent. In this work, based on the MBC notion, a technology-agnostic hybrid model selection policy for Vehicle-to-Everything (V2X) communication is proposed which benefits from the characteristics of the non-parametric Bayesian inference techniques, specifically Gaussian Processes. The results show the effectiveness of the proposed communication architecture on both reducing the required message exchange rate and increasing the remote agent tracking precision.
Tasks	Bayesian Inference, Gaussian Processes, Model Selection
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01576v2
PDF	http://arxiv.org/pdf/1903.01576v2.pdf
PWC	https://paperswithcode.com/paper/v2x-system-architecture-utilizing-hybrid
Repo
Framework

Monotonic Gaussian Process for Spatio-Temporal Disease Progression Modeling in Brain Imaging Data


Title	Monotonic Gaussian Process for Spatio-Temporal Disease Progression Modeling in Brain Imaging Data
Authors	Clement Abi Nader, Nicholas Ayache, Philippe Robert, Marco Lorenzi
Abstract	We introduce a probabilistic generative model for disentangling spatio-temporal disease trajectories from series of high-dimensional brain images. The model is based on spatio-temporal matrix factorization, where inference on the sources is constrained by anatomically plausible statistical priors. To model realistic trajectories, the temporal sources are defined as monotonic and time-reparametrized Gaussian Processes. To account for the non-stationarity of brain images, we model the spatial sources as sparse codes convolved at multiple scales. The method was tested on synthetic data favourably comparing with standard blind source separation approaches. The application on large-scale imaging data from a clinical study allows to disentangle differential temporal progression patterns mapping brain regions key to neurodegeneration, while revealing a disease-specific time scale associated to the clinical diagnosis.
Tasks	Gaussian Processes
Published	2019-02-28
URL	https://arxiv.org/abs/1902.10952v3
PDF	https://arxiv.org/pdf/1902.10952v3.pdf
PWC	https://paperswithcode.com/paper/monotonic-gaussian-process-for-spatio
Repo
Framework

CUDA optimized Neural Network predicts blood glucose control from quantified joint mobility and anthropometrics


Title	CUDA optimized Neural Network predicts blood glucose control from quantified joint mobility and anthropometrics
Authors	Sterling Ramroach, Andrew Dhanoo, Brian Cockburn, Ajay Joshi
Abstract	Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics processing unit (GPU). In this paper, we leveraged the power of Nvidia GPUs to parallelize all of the computation involved in training, to accelerate a backpropagation feed-forward neural network with one hidden layer using CUDA and C++. This optimized neural network was tasked with predicting the level of glycated hemoglobin (HbA1c) from non-invasive markers. The rate of increase in the prevalence of Diabetes Mellitus has resulted in an urgent need for early detection and accurate diagnosis. However, due to the invasiveness and limitations of conventional tests, alternate means are being considered. Limited Joint Mobility (LJM) has been reported as an indicator for poor glycemic control. LJM of the fingers is quantified and its link to HbA1c is investigated along with other potential non-invasive markers of HbA1c. We collected readings of 33 potential markers from 120 participants at a clinic in south Trinidad. Our neural network achieved 95.65% accuracy on the training and 86.67% accuracy on the testing set for male participants and 97.73% and 66.67% accuracy on the training and testing sets for female participants. Using 960 CUDA cores from a Nvidia GeForce GTX 660, our parallelized neural network was trained 50 times faster on both subsets, than its corresponding CPU implementation on an Intel Core (TM) i7-3630QM 2.40 GHz CPU.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07847v1
PDF	https://arxiv.org/pdf/1908.07847v1.pdf
PWC	https://paperswithcode.com/paper/190807847
Repo
Framework

Language is Power: Representing States Using Natural Language in Reinforcement Learning


Title	Language is Power: Representing States Using Natural Language in Reinforcement Learning
Authors	Erez Schwartz, Guy Tennenholtz, Chen Tessler, Shie Mannor
Abstract	Recent advances in reinforcement learning have shown its potential to tackle complex real-life tasks. However, as the dimensionality of the task increases, reinforcement learning methods tend to struggle. To overcome this, we explore methods for representing the semantic information embedded in the state. While previous methods focused on information in its raw form (e.g., raw visual input), we propose to represent the state using natural language. Language can represent complex scenarios and concepts, making it a favorable candidate for representation. Empirical evidence, within the domain of ViZDoom, suggests that natural language based agents are more robust, converge faster and perform better than vision based agents, showing the benefit of using natural language representations for reinforcement learning.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.02789v2
PDF	https://arxiv.org/pdf/1910.02789v2.pdf
PWC	https://paperswithcode.com/paper/natural-language-state-representation-for
Repo
Framework

Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in South Asia


Title	Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in South Asia
Authors	Usman Nazir, Numan Khurshid, Muhammad Ahmed Bhimra, Murtaza Taj
Abstract	This paper proposes to employ a Inception-ResNet inspired deep learning architecture called Tiny-Inception-ResNet-v2 to eliminate bonded labor by identifying brick kilns within “Brick-Kiln-Belt” of South Asia. The framework is developed by training a network on the satellite imagery consisting of 11 different classes of South Asian region. The dataset developed during the process includes the geo-referenced images of brick kilns, houses, roads, tennis courts, farms, sparse trees, dense trees, orchards, parking lots, parks and barren lands. The dataset is made publicly available for further research. Our proposed network architecture with very fewer learning parameters outperforms all state-of-the-art architectures employed for recognition of brick kilns. Our proposed solution would enable regional monitoring and evaluation mechanisms for the Sustainable Development Goals.
Tasks
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05552v1
PDF	https://arxiv.org/pdf/1907.05552v1.pdf
PWC	https://paperswithcode.com/paper/tiny-inception-resnet-v2-using-deep-learning
Repo
Framework

A Utility-Preserving GAN for Face Obscuration


Title	A Utility-Preserving GAN for Face Obscuration
Authors	Hanxiang Hao, David Güera, Amy R. Reibman, Edward J. Delp
Abstract	From TV news to Google StreetView, face obscuration has been used for privacy protection. Due to recent advances in the field of deep learning, obscuration methods such as Gaussian blurring and pixelation are not guaranteed to conceal identity. In this paper, we propose a utility-preserving generative model, UP-GAN, that is able to provide an effective face obscuration, while preserving facial utility. By utility-preserving we mean preserving facial features that do not reveal identity, such as age, gender, skin tone, pose, and expression. We show that the proposed method achieves the best performance in terms of obscuration and utility preservation.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11979v1
PDF	https://arxiv.org/pdf/1906.11979v1.pdf
PWC	https://paperswithcode.com/paper/a-utility-preserving-gan-for-face-obscuration
Repo
Framework

Performance evaluation of deep neural networks for forecasting time-series with multiple structural breaks and high volatility


Title	Performance evaluation of deep neural networks for forecasting time-series with multiple structural breaks and high volatility
Authors	Shikhar Jain, Rohit Kaushik, Siddhant Jain, Tirtharaj Dash
Abstract	The problem of automatic forecasting of time-series data has been a long-standing challenge for the machine learning and forecasting community. The problem is relatively simple when the series is stationary. However, the majority of the real-world time-series problems have non-stationary characteristics making the understanding of the trend and seasonality very complex. Further, it is assumed that the future response is dependent on the past data and, therefore, can be modeled using a function approximator. Our interest in this paper is to study the applicability of the popular deep neural networks (DNN) comprehensively as function approximators for non-stationary time-series forecasting. We employ the following DNN models: Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and RNN with Long-Short Term Memory (LSTM-RNN) and RNN with Gated-Recurrent Unit (GRU-RNN). These powerful DNN methods have been evaluated over popular Indian financial stocks data comprising of five stocks from National Stock Exchange Nifty-50 (NSE-Nifty50), and five stocks from Bombay Stock Exchange 30 (BSE-30). Further, the performance evaluation of these DNNs in terms of their predictive power has been done using two fashions: (1) single-step forecasting, (2) multi-step forecasting. Our extensive simulation experiments on these ten datasets report that the performance of these DNNs for single-step forecasting is pretty convincing as the predictions are found to follow the truely observed values closely. However, we also find that all these DNN models perform miserably in the case of multi-step time-series forecasting, based on the datasets used by us. Consequently, we observe that none of these DNN models are reliable for multi-step time-series forecasting.
Tasks	Time Series, Time Series Forecasting
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06704v1
PDF	https://arxiv.org/pdf/1911.06704v1.pdf
PWC	https://paperswithcode.com/paper/performance-evaluation-of-deep-neural
Repo
Framework

Textual Data for Time Series Forecasting


Title	Textual Data for Time Series Forecasting
Authors	David Obst, Badih Ghattas, Sandra Claudel, Jairo Cugliari, Yannig Goude, Georges Oppenheim
Abstract	While ubiquitous, textual sources of information such as company reports, social media posts, etc. are hardly included in prediction algorithms for time series, despite the relevant information they may contain. In this work, openly accessible daily weather reports from France and the United-Kingdom are leveraged to predict time series of national electricity consumption, average temperature and wind-speed with a single pipeline. Two methods of numerical representation of text are considered, namely traditional Term Frequency - Inverse Document Frequency (TF-IDF) as well as our own neural word embedding. Using exclusively text, we are able to predict the aforementioned time series with sufficient accuracy to be used to replace missing data. Furthermore the proposed word embeddings display geometric properties relating to the behavior of the time series and context similarity between words.
Tasks	Time Series, Time Series Forecasting, Word Embeddings
Published	2019-10-25
URL	https://arxiv.org/abs/1910.12618v2
PDF	https://arxiv.org/pdf/1910.12618v2.pdf
PWC	https://paperswithcode.com/paper/textual-data-for-time-series-forecasting
Repo
Framework

You May Not Need Order in Time Series Forecasting


Title	You May Not Need Order in Time Series Forecasting
Authors	Yunkai Zhang, Qiao Jiang, Shurui Li, Xiaoyong Jin, Xueying Ma, Xifeng Yan
Abstract	Time series forecasting with limited data is a challenging yet critical task. While transformers have achieved outstanding performances in time series forecasting, they often require many training samples due to the large number of trainable parameters. In this paper, we propose a training technique for transformers that prepares the training windows through random sampling. As input time steps need not be consecutive, the number of distinct samples increases from linearly to combinatorially many. By breaking the temporal order, this technique also helps transformers to capture dependencies among time steps in finer granularity. We achieve competitive results compared to the state-of-the-art on real-world datasets.
Tasks	Time Series, Time Series Forecasting
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09620v1
PDF	https://arxiv.org/pdf/1910.09620v1.pdf
PWC	https://paperswithcode.com/paper/you-may-not-need-order-in-time-series
Repo
Framework

Toward an Automatic System for Computer-Aided Assessment in Facial Palsy


Title	Toward an Automatic System for Computer-Aided Assessment in Facial Palsy
Authors	Diego L. Guarin, Yana Yunusova, Babak Taati, Joseph R Dusseldorp, Suresh Mohan, Joana Tavares, Martinus M. van Veen, Emily Fortier, Tessa A. Hadlock, Nate Jowett
Abstract	Importance: Machine learning (ML) approaches to facial landmark localization carry great clinical potential for quantitative assessment of facial function as they enable high-throughput automated quantification of relevant facial metrics from photographs. However, translation from research settings to clinical applications requires important improvements. Objective: To develop an ML algorithm for accurate facial landmarks localization in photographs of facial palsy patients, and use it as part of an automated computer-aided diagnosis system. Design, Setting, and Participants: Facial landmarks were manually localized in portrait photographs of eight expressions obtained from 200 facial palsy patients and 10 controls. A novel ML model for automated facial landmark localization was trained using this disease-specific database. Model output was compared to manual annotations and the output of a model trained using a larger database consisting only of healthy subjects. Model accuracy was evaluated by the normalized root mean square error (NRMSE) between algorithms’ prediction and manual annotations. Results: Publicly available algorithms provide poor results when applied to patients compared to healthy controls (NRMSE, 8.56 +/- 2.16 vs. 7.09 +/- 2.34, p « 0.01). We found significant improvement in facial landmark localization accuracy for the clinical population when using a model trained with a relatively small number patients’ photographs (1440) compared to a model trained using several thousand more images of healthy faces (NRMSE, 6.03 +/- 2.43 vs. 8.56 +/- 2.16, p « 0.01). Conclusions: Retraining a landmark detection model with a small number of clinical images significantly improved landmark detection performance in frontal view photographs of the clinical population. These results represent the first steps towards an automatic system for computer-aided assessment in facial palsy.
Tasks	Face Alignment
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11497v1
PDF	https://arxiv.org/pdf/1910.11497v1.pdf
PWC	https://paperswithcode.com/paper/toward-an-automatic-system-for-computer-aided
Repo
Framework