October 17, 2019

3208 words 16 mins read

Paper Group ANR 788

Stochastic Optimal Control of Epidemic Processes in Networks. Decision Provenance: Harnessing data flow for accountable systems. Simultaneous Recognition of Horizontal and Vertical Text in Natural Images. Fast and Accurate Tumor Segmentation of Histology Images using Persistent Homology and Deep Convolutional Features. Facial Expression Recognition …

Stochastic Optimal Control of Epidemic Processes in Networks


Title	Stochastic Optimal Control of Epidemic Processes in Networks
Authors	Lars Lorch, Abir De, Samir Bhatt, William Trouleau, Utkarsh Upadhyay, Manuel Gomez-Rodriguez
Abstract	We approach the development of models and control strategies of susceptible-infected-susceptible (SIS) epidemic processes from the perspective of marked temporal point processes and stochastic optimal control of stochastic differential equations (SDEs) with jumps. In contrast to previous work, this novel perspective is particularly well-suited to make use of fine-grained data about disease outbreaks and lets us overcome the shortcomings of current control strategies. Our control strategy resorts to treatment intensities to determine who to treat and when to do so to minimize the amount of infected individuals over time. Preliminary experiments with synthetic data show that our control strategy consistently outperforms several alternatives. Looking into the future, we believe our methodology provides a promising step towards the development of practical data-driven control strategies of epidemic processes.
Tasks	Point Processes
Published	2018-10-30
URL	http://arxiv.org/abs/1810.13043v4
PDF	http://arxiv.org/pdf/1810.13043v4.pdf
PWC	https://paperswithcode.com/paper/stochastic-optimal-control-of-epidemic
Repo
Framework

Decision Provenance: Harnessing data flow for accountable systems


Title	Decision Provenance: Harnessing data flow for accountable systems
Authors	Jatinder Singh, Jennifer Cobbe, Chris Norval
Abstract	Demand is growing for more accountability regarding the technological systems that increasingly occupy our world. However, the complexity of many of these systems - often systems-of-systems - poses accountability challenges. A key reason for this is because the details and nature of the information flows that interconnect and drive systems, which often occur across technical and organisational boundaries, tend to be invisible or opaque. This paper argues that data provenance methods show much promise as a technical means for increasing the transparency of these interconnected systems. Specifically, given the concerns regarding ever-increasing levels of automated and algorithmic decision-making, and so-called ‘algorithmic systems’ in general, we propose decision provenance as a concept showing much promise. Decision provenance entails using provenance methods to provide information exposing decision pipelines: chains of inputs to, the nature of, and the flow-on effects from the decisions and actions taken (at design and run-time) throughout systems. This paper introduces the concept of decision provenance, and takes an interdisciplinary (tech-legal) exploration into its potential for assisting accountability in algorithmic systems. We argue that decision provenance can help facilitate oversight, audit, compliance, risk mitigation, and user empowerment, and we also indicate the implementation considerations and areas for research necessary for realising its vision. More generally, we make the case that considerations of data flow, and systems more broadly, are important to discussions of accountability, and complement the considerable attention already given to algorithmic specifics.
Tasks	Decision Making
Published	2018-04-16
URL	https://arxiv.org/abs/1804.05741v4
PDF	https://arxiv.org/pdf/1804.05741v4.pdf
PWC	https://paperswithcode.com/paper/decision-provenance-harnessing-data-flow-for
Repo
Framework

Simultaneous Recognition of Horizontal and Vertical Text in Natural Images


Title	Simultaneous Recognition of Horizontal and Vertical Text in Natural Images
Authors	Chankyu Choi, Youngmin Yoon, Junsu Lee, Junseok Kim
Abstract	Recent state-of-the-art scene text recognition methods have primarily focused on horizontal text in images. However, in several Asian countries, including China, large amounts of text in signs, books, and TV commercials are vertically directed. Because the horizontal and vertical texts exhibit different characteristics, developing an algorithm that can simultaneously recognize both types of text in real environments is necessary. To address this problem, we adopted the direction encoding mask (DEM) and selective attention network (SAN) methods based on supervised learning. DEM contains directional information to compensate in cases that lack text direction; therefore, our network is trained using this information to handle the vertical text. The SAN method is designed to work individually for both types of text. To train the network to recognize both types of text and to evaluate the effectiveness of the designed model, we prepared a new synthetic vertical text dataset and collected an actual vertical text dataset (VTD142) from the Web. Using these datasets, we proved that our proposed model can accurately recognize both vertical and horizontal text and can achieve state-of-the-art results in experiments using benchmark datasets, including the street view test (SVT), IIIT-5k, and ICDAR. Although our model is relatively simple as compared to its predecessors, it maintains the accuracy and is trained in an end-to-end manner.
Tasks	Scene Text Recognition
Published	2018-12-06
URL	http://arxiv.org/abs/1812.07059v1
PDF	http://arxiv.org/pdf/1812.07059v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-recognition-of-horizontal-and
Repo
Framework

Fast and Accurate Tumor Segmentation of Histology Images using Persistent Homology and Deep Convolutional Features


Title	Fast and Accurate Tumor Segmentation of Histology Images using Persistent Homology and Deep Convolutional Features
Authors	Talha Qaiser, Yee-Wah Tsang, Daiki Taniyama, Naoya Sakamoto, Kazuaki Nakane, David Epstein, Nasir Rajpoot
Abstract	Tumor segmentation in whole-slide images of histology slides is an important step towards computer-assisted diagnosis. In this work, we propose a tumor segmentation framework based on the novel concept of persistent homology profiles (PHPs). For a given image patch, the homology profiles are derived by efficient computation of persistent homology, which is an algebraic tool from homology theory. We propose an efficient way of computing topological persistence of an image, alternative to simplicial homology. The PHPs are devised to distinguish tumor regions from their normal counterparts by modeling the atypical characteristics of tumor nuclei. We propose two variants of our method for tumor segmentation: one that targets speed without compromising accuracy and the other that targets higher accuracy. The fast version is based on the selection of exemplar image patches from a convolution neural network (CNN) and patch classification by quantifying the divergence between the PHPs of exemplars and the input image patch. Detailed comparative evaluation shows that the proposed algorithm is significantly faster than competing algorithms while achieving comparable results. The accurate version combines the PHPs and high-level CNN features and employs a multi-stage ensemble strategy for image patch labeling. Experimental results demonstrate that the combination of PHPs and CNN features outperforms competing algorithms. This study is performed on two independently collected colorectal datasets containing adenoma, adenocarcinoma, signet and healthy cases. Collectively, the accurate tumor segmentation produces the highest average patch-level F1-score, as compared with competing algorithms, on malignant and healthy cases from both the datasets. Overall the proposed framework highlights the utility of persistent homology for histopathology image analysis.
Tasks
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03699v1
PDF	http://arxiv.org/pdf/1805.03699v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-tumor-segmentation-of
Repo
Framework

Facial Expression Recognition using Facial Landmark Detection and Feature Extraction via Neural Networks


Title	Facial Expression Recognition using Facial Landmark Detection and Feature Extraction via Neural Networks
Authors	Fuzail Khan
Abstract	The proposed framework in this paper has the primary objective of classifying the facial expression shown by a person. These classifiable expressions can be any one of the six universal emotions along with the neutral emotion. After the initial facial localization is performed, facial landmark detection and feature extraction are applied where in the landmarks are determined to be the fiducial features: the eyebrows, eyes, nose and lips. This is primarily done using the Sobel operator and the Hough transform followed by Shi Tomasi corner point detection. This leads to input feature vectors being formulated using Euclidean distances and trained into a Multi-Layer Perceptron (MLP) neural network in order to classify the expression being displayed. The results achieved have further dealt with higher uniformity in certain emotions and the inherently subjective nature of expression.
Tasks	Facial Expression Recognition, Facial Landmark Detection
Published	2018-12-10
URL	http://arxiv.org/abs/1812.04510v2
PDF	http://arxiv.org/pdf/1812.04510v2.pdf
PWC	https://paperswithcode.com/paper/facial-expression-recognition-using-facial
Repo
Framework

Clustering with Temporal Constraints on Spatio-Temporal Data of Human Mobility


Title	Clustering with Temporal Constraints on Spatio-Temporal Data of Human Mobility
Authors	Yunlong Wang, Bjoern Sommer, Falk Schreiber, Harald Reiterer
Abstract	Extracting significant places or places of interest (POIs) using individuals’ spatio-temporal data is of fundamental importance for human mobility analysis. Classical clustering methods have been used in prior work for detecting POIs, but without considering temporal constraints. Usually, the involved parameters for clustering are difficult to determine, e.g., the optimal cluster number in hierarchical clustering. Currently, researchers either choose heuristic values or use spatial distance-based optimization to determine an appropriate parameter set. We argue that existing research does not optimally address temporal information and thus leaves much room for improvement. Considering temporal constraints in human mobility, we introduce an effective clustering approach - namely POI clustering with temporal constraints (PC-TC) - to extract POIs from spatio-temporal data of human mobility. Following human mobility nature in modern society, our approach aims to extract both global POIs (e.g., workplace or university) and local POIs (e.g., library, lab, and canteen). Based on two publicly available datasets including 193 individuals, our evaluation results show that PC-TC has much potential for next place prediction in terms of granularity (i.e., the number of extracted POIs) and predictability.
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00546v1
PDF	http://arxiv.org/pdf/1807.00546v1.pdf
PWC	https://paperswithcode.com/paper/clustering-with-temporal-constraints-on
Repo
Framework

The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks


Title	The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks
Authors	George Philipp, Jaime G. Carbonell
Abstract	For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients, though even this guideline has remained relatively vague and circumstantial. We introduce the nonlinearity coefficient (NLC), a measurement of the complexity of the function computed by a neural network that is based on the magnitude of the gradient. Via an extensive empirical study, we show that the NLC is a powerful predictor of test error and that attaining a right-sized NLC is essential for optimal performance. The NLC exhibits a range of intriguing and important properties. It is closely tied to the amount of information gained from computing a single network gradient. It is tied to the error incurred when replacing the nonlinearity operations in the network with linear operations. It is not susceptible to the confounders of multiplicative scaling, additive bias and layer width. It is stable from layer to layer. Hence, we argue that the NLC is the first robust predictor of overfitting in deep networks.
Tasks
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00179v2
PDF	http://arxiv.org/pdf/1806.00179v2.pdf
PWC	https://paperswithcode.com/paper/the-nonlinearity-coefficient-predicting
Repo
Framework

Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy Maximization


Title	Improving the Stability of the Knockoff Procedure: Multiple Simultaneous Knockoffs and Entropy Maximization
Authors	Jaime Roquero Gimenez, James Zou
Abstract	The Model-X knockoff procedure has recently emerged as a powerful approach for feature selection with statistical guarantees. The advantage of knockoff is that if we have a good model of the features X, then we can identify salient features without knowing anything about how the outcome Y depends on X. An important drawback of knockoffs is its instability: running the procedure twice can result in very different selected features, potentially leading to different conclusions. Addressing this instability is critical for obtaining reproducible and robust results. Here we present a generalization of the knockoff procedure that we call simultaneous multi-knockoffs. We show that multi-knockoff guarantees false discovery rate (FDR) control, and is substantially more stable and powerful compared to the standard (single) knockoff. Moreover we propose a new algorithm based on entropy maximization for generating Gaussian multi-knockoffs. We validate the improved stability and power of multi-knockoffs in systematic experiments. We also illustrate how multi-knockoffs can improve the accuracy of detecting genetic mutations that are causally linked to phenotypes.
Tasks	Feature Selection
Published	2018-10-26
URL	https://arxiv.org/abs/1810.11378v2
PDF	https://arxiv.org/pdf/1810.11378v2.pdf
PWC	https://paperswithcode.com/paper/improving-the-stability-of-the-knockoff
Repo
Framework

Evolvement Constrained Adversarial Learning for Video Style Transfer


Title	Evolvement Constrained Adversarial Learning for Video Style Transfer
Authors	Wenbo Li, Longyin Wen, Xiao Bian, Siwei Lyu
Abstract	Video style transfer is a useful component for applications such as augmented reality, non-photorealistic rendering, and interactive games. Many existing methods use optical flow to preserve the temporal smoothness of the synthesized video. However, the estimation of optical flow is sensitive to occlusions and rapid motions. Thus, in this work, we introduce a novel evolve-sync loss computed by evolvements to replace optical flow. Using this evolve-sync loss, we build an adversarial learning framework, termed as Video Style Transfer Generative Adversarial Network (VST-GAN), which improves upon the MGAN method for image style transfer for more efficient video style transfer. We perform extensive experimental evaluations of our method and show quantitative and qualitative improvements over the state-of-the-art methods.
Tasks	Optical Flow Estimation, Style Transfer, Video Style Transfer
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02476v1
PDF	http://arxiv.org/pdf/1811.02476v1.pdf
PWC	https://paperswithcode.com/paper/evolvement-constrained-adversarial-learning
Repo
Framework

CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling


Title	CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling
Authors	Heike Adel, Hinrich Schütze
Abstract	This paper describes the CIS slot filling system for the TAC Cold Start evaluations 2015. It extends and improves the system we have built for the evaluation last year. This paper mainly describes the changes to our last year’s system. Especially, it focuses on the coreference and classification component. For coreference, we have performed several analysis and prepared a resource to simplify our end-to-end system and improve its runtime. For classification, we propose to use neural networks. We have trained convolutional and recurrent neural networks and combined them with traditional evaluation methods, namely patterns and support vector machines. Our runs for the 2015 evaluation have been designed to directly assess the effect of each network on the end-to-end performance of the system. The CIS system achieved rank 3 of all slot filling systems participating in the task.
Tasks	Coreference Resolution, Slot Filling
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02230v1
PDF	http://arxiv.org/pdf/1811.02230v1.pdf
PWC	https://paperswithcode.com/paper/cis-at-tac-cold-start-2015-neural-networks
Repo
Framework

DT-LET: Deep Transfer Learning by Exploring where to Transfer


Title	DT-LET: Deep Transfer Learning by Exploring where to Transfer
Authors	Jianzhe Lin, Qi Wang, Rabab Ward, Z. Jane Wang
Abstract	Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn’t always hold true, especially when the data from the two domains are heterogeneous with different resolutions. In such case, the most suitable numbers of layers for the source domain data and the target domain data would differ. As a result, the high level knowledge from the source domain would be transferred to the wrong layer of target domain. Based on this observation, “where to transfer” proposed in this paper should be a novel research frontier. We propose a new mathematic model named DT-LET to solve this heterogeneous transfer learning problem. In order to select the best matching of layers to transfer knowledge, we define specific loss function to estimate the corresponding relationship between high-level features of data in the source domain and the target domain. To verify this proposed cross-layer model, experiments for two cross-domain recognition/classification tasks are conducted, and the achieved superior results demonstrate the necessity of layer correspondence searching.
Tasks	Transfer Learning
Published	2018-09-23
URL	http://arxiv.org/abs/1809.08541v1
PDF	http://arxiv.org/pdf/1809.08541v1.pdf
PWC	https://paperswithcode.com/paper/dt-let-deep-transfer-learning-by-exploring
Repo
Framework

A hybrid econometric-machine learning approach for relative importance analysis: Prioritizing food policy


Title	A hybrid econometric-machine learning approach for relative importance analysis: Prioritizing food policy
Authors	Akash Malhotra
Abstract	A measure of relative importance of variables is often desired by researchers when the explanatory aspects of econometric methods are of interest. To this end, the author briefly reviews the limitations of conventional econometrics in constructing a reliable measure of variable importance. The author highlights the relative stature of explanatory and predictive analysis in economics and the emergence of fruitful collaborations between econometrics and computer science. Learning lessons from both, the author proposes a hybrid approach based on conventional econometrics and advanced machine learning (ML) algorithms, which are otherwise, used in predictive analytics. The purpose of this article is two-fold, to propose a hybrid approach to assess relative importance and demonstrate its applicability in addressing policy priority issues with an example of food inflation in India, followed by a broader aim to introduce the possibility of conflation of ML and conventional econometrics to an audience of researchers in economics and social sciences, in general
Tasks
Published	2018-06-09
URL	https://arxiv.org/abs/1806.04517v2
PDF	https://arxiv.org/pdf/1806.04517v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-econometric-machine-learning
Repo
Framework

Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots


Title	Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots
Authors	Francisco J. Chiyah Garcia, David A. Robb, Xingkun Liu, Atanas Laskov, Pedro Patron, Helen Hastie
Abstract	Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that enables vehicle behaviour to be queried by the user. We obtain an interpretable model of autonomy through having an expert ‘speak out-loud’ and provide explanations during a mission. This approach is agnostic to the type of autonomy model and as expert and operator are from the same user-group, we predict that these explanations will align well with the operator’s mental model, increase transparency and assist with operator training.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02088v1
PDF	http://arxiv.org/pdf/1803.02088v1.pdf
PWC	https://paperswithcode.com/paper/explain-yourself-a-natural-language-interface
Repo
Framework

Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization


Title	Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
Authors	Umut Şimşekli, Çağatay Yıldız, Thanh Huy Nguyen, Gaël Richard, A. Taylan Cemgil
Abstract	Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By building up on this recent theory, in this study, we develop an asynchronous-parallel stochastic L-BFGS algorithm for non-convex optimization. The proposed algorithm is suitable for both distributed and shared-memory settings. We provide formal theoretical analysis and show that the proposed method achieves an ergodic convergence rate of ${\cal O}(1/\sqrt{N})$ ($N$ being the total number of iterations) and it can achieve a linear speedup under certain conditions. We perform several experiments on both synthetic and real datasets. The results support our theory and show that the proposed algorithm provides a significant speedup over the recently proposed synchronous distributed L-BFGS algorithm.
Tasks
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02617v1
PDF	http://arxiv.org/pdf/1806.02617v1.pdf
PWC	https://paperswithcode.com/paper/asynchronous-stochastic-quasi-newton-mcmc-for
Repo
Framework

A Unified Multilingual Handwriting Recognition System using multigrams sub-lexical units


Title	A Unified Multilingual Handwriting Recognition System using multigrams sub-lexical units
Authors	Wassim Swaileh, Yann Soullard, Thierry Paquet
Abstract	We address the design of a unified multilingual system for handwriting recognition. Most of multi- lingual systems rests on specialized models that are trained on a single language and one of them is selected at test time. While some recognition systems are based on a unified optical model, dealing with a unified language model remains a major issue, as traditional language models are generally trained on corpora composed of large word lexicons per language. Here, we bring a solution by con- sidering language models based on sub-lexical units, called multigrams. Dealing with multigrams strongly reduces the lexicon size and thus decreases the language model complexity. This makes pos- sible the design of an end-to-end unified multilingual recognition system where both a single optical model and a single language model are trained on all the languages. We discuss the impact of the language unification on each model and show that our system reaches state-of-the-art methods perfor- mance with a strong reduction of the complexity.
Tasks	Language Modelling
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09183v1
PDF	http://arxiv.org/pdf/1808.09183v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-multilingual-handwriting
Repo
Framework