July 28, 2019

3125 words 15 mins read

Paper Group ANR 447

Machine learning & artificial intelligence in the quantum domain. Question Answering from Unstructured Text by Retrieval and Comprehension. Scalable Nonlinear AUC Maximization Methods. DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition. Near-Optimal Discrete Optimization for Experimental Design: A Regret …

Machine learning & artificial intelligence in the quantum domain


Title	Machine learning & artificial intelligence in the quantum domain
Authors	Vedran Dunjko, Hans J. Briegel
Abstract	Quantum information technologies, and intelligent learning systems, are both emergent technologies that will likely have a transforming impact on our society. The respective underlying fields of research – quantum information (QI) versus machine learning (ML) and artificial intelligence (AI) – have their own specific challenges, which have hitherto been investigated largely independently. However, in a growing body of recent work, researchers have been probing the question to what extent these fields can learn and benefit from each other. QML explores the interaction between quantum computing and ML, investigating how results and techniques from one field can be used to solve the problems of the other. Recently, we have witnessed breakthroughs in both directions of influence. For instance, quantum computing is finding a vital application in providing speed-ups in ML, critical in our “big data” world. Conversely, ML already permeates cutting-edge technologies, and may become instrumental in advanced quantum technologies. Aside from quantum speed-up in data analysis, or classical ML optimization used in quantum experiments, quantum enhancements have also been demonstrated for interactive learning, highlighting the potential of quantum-enhanced learning agents. Finally, works exploring the use of AI for the very design of quantum experiments, and for performing parts of genuine research autonomously, have reported their first successes. Beyond the topics of mutual enhancement, researchers have also broached the fundamental issue of quantum generalizations of ML/AI concepts. This deals with questions of the very meaning of learning and intelligence in a world that is described by quantum mechanics. In this review, we describe the main ideas, recent developments, and progress in a broad spectrum of research investigating machine learning and artificial intelligence in the quantum domain.
Tasks
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02779v1
PDF	http://arxiv.org/pdf/1709.02779v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-artificial-intelligence-in
Repo
Framework

Question Answering from Unstructured Text by Retrieval and Comprehension


Title	Question Answering from Unstructured Text by Retrieval and Comprehension
Authors	Yusuke Watanabe, Bhuwan Dhingra, Ruslan Salakhutdinov
Abstract	Open domain Question Answering (QA) systems must interact with external knowledge sources, such as web pages, to find relevant information. Information sources like Wikipedia, however, are not well structured and difficult to utilize in comparison with Knowledge Bases (KBs). In this work we present a two-step approach to question answering from unstructured text, consisting of a retrieval step and a comprehension step. For comprehension, we present an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary. For retrieval we introduce a hand-crafted model and a neural model for ranking relevant articles. We achieve state-of-the-art performance on W IKI M OVIES dataset, reducing the error by 40%. Our experimental results further demonstrate the importance of each of the introduced components.
Tasks	Open-Domain Question Answering, Question Answering
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08885v1
PDF	http://arxiv.org/pdf/1703.08885v1.pdf
PWC	https://paperswithcode.com/paper/question-answering-from-unstructured-text-by
Repo
Framework

Scalable Nonlinear AUC Maximization Methods


Title	Scalable Nonlinear AUC Maximization Methods
Authors	Majdi Khalid, Indrakshi Ray, Hamidreza Chitsaz
Abstract	The area under the ROC curve (AUC) is a measure of interest in various machine learning and data mining applications. It has been widely used to evaluate classification performance on heavily imbalanced data. The kernelized AUC maximization machines have established a superior generalization ability compared to linear AUC machines because of their capability in modeling the complex nonlinear structure underlying most real-world data. However, the high training complexity renders the kernelized AUC machines infeasible for large-scale data. In this paper, we present two nonlinear AUC maximization algorithms that optimize pairwise linear classifiers over a finite-dimensional feature space constructed via the k-means Nystr"{o}m method. Our first algorithm maximize the AUC metric by optimizing a pairwise squared hinge loss function using the truncated Newton method. However, the second-order batch AUC maximization method becomes expensive to optimize for extremely massive datasets. This motivate us to develop a first-order stochastic AUC maximization algorithm that incorporates a scheduled regularization update and scheduled averaging techniques to accelerate the convergence of the classifier. Experiments on several benchmark datasets demonstrate that the proposed AUC classifiers are more efficient than kernelized AUC machines while they are able to surpass or at least match the AUC performance of the kernelized AUC machines. The experiments also show that the proposed stochastic AUC classifier outperforms the state-of-the-art online AUC maximization methods in terms of AUC classification accuracy.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00760v4
PDF	http://arxiv.org/pdf/1710.00760v4.pdf
PWC	https://paperswithcode.com/paper/scalable-nonlinear-auc-maximization-methods
Repo
Framework

DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition


Title	DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition
Authors	Benjamin Planche, Ziyan Wu, Kai Ma, Shanhui Sun, Stefan Kluckner, Terrence Chen, Andreas Hutter, Sergey Zakharov, Harald Kosch, Jan Ernst
Abstract	Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on synthetic data for their training. For depth images however, discrepancies with real scans still noticeably affect the end performance. We thus propose an end-to-end framework which simulates the whole mechanism of these devices, generating realistic depth data from 3D models by comprehensively modeling vital factors e.g. sensor noise, material reflectance, surface geometry. Not only does our solution cover a wider range of sensors and achieve more realistic results than previous methods, assessed through extended evaluation, but we go further by measuring the impact on the training of neural networks for various recognition tasks; demonstrating how our pipeline seamlessly integrates such architectures and consistently enhances their performance.
Tasks	Synthetic Data Generation
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08558v2
PDF	http://arxiv.org/pdf/1702.08558v2.pdf
PWC	https://paperswithcode.com/paper/depthsynth-real-time-realistic-synthetic-data
Repo
Framework

Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approach


Title	Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approach
Authors	Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang
Abstract	The experimental design problem concerns the selection of k points from a potentially large design pool of p-dimensional vectors, so as to maximize the statistical efficiency regressed on the selected k design points. Statistical efficiency is measured by optimality criteria, including A(verage), D(eterminant), T(race), E(igen), V(ariance) and G-optimality. Except for the T-optimality, exact optimization is NP-hard. We propose a polynomial-time regret minimization framework to achieve a $(1+\varepsilon)$ approximation with only $O(p/\varepsilon^2)$ design points, for all the optimality criteria above. In contrast, to the best of our knowledge, before our work, no polynomial-time algorithm achieves $(1+\varepsilon)$ approximations for D/E/G-optimality, and the best poly-time algorithm achieving $(1+\varepsilon)$-approximation for A/V-optimality requires $k = \Omega(p^2/\varepsilon)$ design points.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.05174v1
PDF	http://arxiv.org/pdf/1711.05174v1.pdf
PWC	https://paperswithcode.com/paper/near-optimal-discrete-optimization-for
Repo
Framework

Gauging Variational Inference


Title	Gauging Variational Inference
Authors	Sungsoo Ahn, Michael Chertkov, Jinwoo Shin
Abstract	Computing partition function is the most important statistical inference task arising in applications of Graphical Models (GM). Since it is computationally intractable, approximate methods have been used to resolve the issue in practice, where mean-field (MF) and belief propagation (BP) are arguably the most popular and successful approaches of a variational type. In this paper, we propose two new variational schemes, coined Gauged-MF (G-MF) and Gauged-BP (G-BP), improving MF and BP, respectively. Both provide lower bounds for the partition function by utilizing the so-called gauge transformation which modifies factors of GM while keeping the partition function invariant. Moreover, we prove that both G-MF and G-BP are exact for GMs with a single loop of a special structure, even though the bare MF and BP perform badly in this case. Our extensive experiments, on complete GMs of relatively small size and on large GM (up-to 300 variables) confirm that the newly proposed algorithms outperform and generalize MF and BP.
Tasks
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01056v5
PDF	http://arxiv.org/pdf/1703.01056v5.pdf
PWC	https://paperswithcode.com/paper/gauging-variational-inference
Repo
Framework

AppLP: A Dialogue on Applications of Logic Programming


Title	AppLP: A Dialogue on Applications of Logic Programming
Authors	David S. Warren, Yanhong A. Liu
Abstract	This document describes the contributions of the 2016 Applications of Logic Programming Workshop (AppLP), which was held on October 17 and associated with the International Conference on Logic Programming (ICLP) in Flushing, New York City.
Tasks
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02375v1
PDF	http://arxiv.org/pdf/1704.02375v1.pdf
PWC	https://paperswithcode.com/paper/applp-a-dialogue-on-applications-of-logic
Repo
Framework

Order embeddings and character-level convolutions for multimodal alignment


Title	Order embeddings and character-level convolutions for multimodal alignment
Authors	Jônatas Wehrmann, Anderson Mattjie, Rodrigo C. Barros
Abstract	With the novel and fast advances in the area of deep neural networks, several challenging image-based tasks have been recently approached by researchers in pattern recognition and computer vision. In this paper, we address one of these tasks, which is to match image content with natural language descriptions, sometimes referred as multimodal content retrieval. Such a task is particularly challenging considering that we must find a semantic correspondence between captions and the respective image, a challenge for both computer vision and natural language processing areas. For such, we propose a novel multimodal approach based solely on convolutional neural networks for aligning images with their captions by directly convolving raw characters. Our proposed character-based textual embeddings allow the replacement of both word-embeddings and recurrent neural networks for text understanding, saving processing time and requiring fewer learnable parameters. Our method is based on the idea of projecting both visual and textual information into a common embedding space. For training such embeddings we optimize a contrastive loss function that is computed to minimize order-violations between images and their respective descriptions. We achieve state-of-the-art performance in the largest and most well-known image-text alignment dataset, namely Microsoft COCO, with a method that is conceptually much simpler and that possesses considerably fewer parameters than current approaches.
Tasks	Word Embeddings
Published	2017-06-03
URL	http://arxiv.org/abs/1706.00999v1
PDF	http://arxiv.org/pdf/1706.00999v1.pdf
PWC	https://paperswithcode.com/paper/order-embeddings-and-character-level
Repo
Framework

LitStoryTeller: An Interactive System for Visual Exploration of Scientific Papers Leveraging Named entities and Comparative Sentences


Title	LitStoryTeller: An Interactive System for Visual Exploration of Scientific Papers Leveraging Named entities and Comparative Sentences
Authors	Qing Ping, Chaomei Chen
Abstract	The present study proposes LitStoryTeller, an interactive system for visually exploring the semantic structure of a scientific article. We demonstrate how LitStoryTeller could be used to answer some of the most fundamental research questions, such as how a new method was built on top of existing methods, based on what theoretical proof and experimental evidences. More importantly, LitStoryTeller can assist users to understand the full and interesting story a scientific paper, with a concise outline and important details. The proposed system borrows a metaphor from screen play, and visualizes the storyline of a scientific paper by arranging its characters (scientific concepts or terminologies) and scenes (paragraphs/sentences) into a progressive and interactive storyline. Such storylines help to preserve the semantic structure and logical thinking process of a scientific paper. Semantic structures, such as scientific concepts and comparative sentences, are extracted using existing named entity recognition APIs and supervised classifiers, from a scientific paper automatically. Two supplementary views, ranked entity frequency view and entity co-occurrence network view, are provided to help users identify the “main plot” of such scientific storylines. When collective documents are ready, LitStoryTeller also provides a temporal entity evolution view and entity community view for collection digestion.
Tasks	Named Entity Recognition
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02214v3
PDF	http://arxiv.org/pdf/1708.02214v3.pdf
PWC	https://paperswithcode.com/paper/litstoryteller-an-interactive-system-for
Repo
Framework

Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder


Title	Gender and Ethnicity Classification of Iris Images using Deep Class-Encoder
Authors	Maneet Singh, Shruti Nagpal, Mayank Vatsa, Richa Singh, Afzel Noore, Angshul Majumdar
Abstract	Soft biometric modalities have shown their utility in different applications including reducing the search space significantly. This leads to improved recognition performance, reduced computation time, and faster processing of test samples. Some common soft biometric modalities are ethnicity, gender, age, hair color, iris color, presence of facial hair or moles, and markers. This research focuses on performing ethnicity and gender classification on iris images. We present a novel supervised autoencoder based approach, Deep Class-Encoder, which uses class labels to learn discriminative representation for the given sample by mapping the learned feature vector to its label. The proposed model is evaluated on two datasets each for ethnicity and gender classification. The results obtained using the proposed Deep Class-Encoder demonstrate its effectiveness in comparison to existing approaches and state-of-the-art methods.
Tasks
Published	2017-10-08
URL	http://arxiv.org/abs/1710.02856v1
PDF	http://arxiv.org/pdf/1710.02856v1.pdf
PWC	https://paperswithcode.com/paper/gender-and-ethnicity-classification-of-iris
Repo
Framework

WebVision Database: Visual Learning and Understanding from Web Data


Title	WebVision Database: Visual Learning and Understanding from Web Data
Authors	Wen Li, Limin Wang, Wei Li, Eirikur Agustsson, Luc Van Gool
Abstract	In this paper, we present a study on learning visual recognition models from large scale noisy web data. We build a new database called WebVision, which contains more than $2.4$ million web images crawled from the Internet by using queries generated from the 1,000 semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information along with those web images (e.g., title, description, tags, etc.) are also crawled. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. Based on our new database, we obtain a few interesting observations: 1) the noisy web images are sufficient for training a good deep CNN model for visual recognition; 2) the model learnt from our WebVision database exhibits comparable or even better generalization ability than the one trained from the ILSVRC 2012 dataset when being transferred to new datasets and tasks; 3) a domain adaptation issue (a.k.a., dataset bias) is observed, which means the dataset can be used as the largest benchmark dataset for visual domain adaptation. Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.
Tasks	Domain Adaptation
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02862v1
PDF	http://arxiv.org/pdf/1708.02862v1.pdf
PWC	https://paperswithcode.com/paper/webvision-database-visual-learning-and
Repo
Framework

A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild


Title	A Jointly Learned Deep Architecture for Facial Attribute Analysis and Face Detection in the Wild
Authors	Keke He, Yanwei Fu, Xiangyang Xue
Abstract	Facial attribute analysis in the real world scenario is very challenging mainly because of complex face variations. Existing works of analyzing face attributes are mostly based on the cropped and aligned face images. However, this result in the capability of attribute prediction heavily relies on the preprocessing of face detector. To address this problem, we present a novel jointly learned deep architecture for both facial attribute analysis and face detection. Our framework can process the natural images in the wild and our experiments on CelebA and LFWA datasets clearly show that the state-of-the-art performance is obtained.
Tasks	Face Detection
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08705v1
PDF	http://arxiv.org/pdf/1707.08705v1.pdf
PWC	https://paperswithcode.com/paper/a-jointly-learned-deep-architecture-for
Repo
Framework

La production de nitrites lors de la dénitrification des eaux usées par biofiltration - Stratégie de contrôle et de réduction des concentrations résiduelles


Title	La production de nitrites lors de la dénitrification des eaux usées par biofiltration - Stratégie de contrôle et de réduction des concentrations résiduelles
Authors	Vincent Rocher, Cédric Join, Stéphane Mottelet, Jean Bernier, Sabrina Rechdaoui-Guérin, Sam Azimi, Paul Lessard, André Pauss, Michel Fliess
Abstract	The recent popularity of post-denitrification processes in the greater Paris area wastewater treatment plants has caused a resurgence of the presence of nitrite in the Seine river. Controlling the production of nitrite during the post-denitrification has thus become a major technical issue. Research studies have been led in the MOCOPEE program (www.mocopee.com) to better understand the underlying mechanisms behind the production of nitrite during wastewater denitrification and to develop technical tools (measurement and control solutions) to assist on-site reductions of nitrite productions. Prior studies have shown that typical methanol dosage strategies produce a varying carbon-to-nitrogen ratio in the reactor, which in turn leads to unstable nitrite concentrations in the effluent. The possibility of adding a model-free control to the actual classical dosage strategy has thus been tested on the SimBio model, which simulates the behavior of wastewater biofilters. The corresponding “intelligent” feedback loop, which is using effluent nitrite concentrations, compensates the classical strategy only when needed. Simulation results show a clear improvement in average nitrite concentration level and level stability in the effluent, without a notable overcost in methanol.
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10868v1
PDF	http://arxiv.org/pdf/1711.10868v1.pdf
PWC	https://paperswithcode.com/paper/la-production-de-nitrites-lors-de-la
Repo
Framework

The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching


Title	The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
Authors	Qian Yu, Xiaobin Chang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales
Abstract	Many vision problems require matching images of object instances across different domains. These include fine-grained sketch-based image retrieval (FG-SBIR) and Person Re-identification (person ReID). Existing approaches attempt to learn a joint embedding space where images from different domains can be directly compared. In most cases, this space is defined by the output of the final layer of a deep neural network (DNN), which primarily contains features of a high semantic level. In this paper, we argue that both high and mid-level features are relevant for cross-domain instance matching (CDIM). Importantly, mid-level features already exist in earlier layers of the DNN. They just need to be extracted, represented, and fused properly with the final layer. Based on this simple but powerful idea, we propose a unified framework for CDIM. Instantiating our framework for FG-SBIR and ReID, we show that our simple models can easily beat the state-of-the-art models, which are often equipped with much more elaborate architectures.
Tasks	Image Retrieval, Person Re-Identification, Sketch-Based Image Retrieval
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08106v2
PDF	http://arxiv.org/pdf/1711.08106v2.pdf
PWC	https://paperswithcode.com/paper/the-devil-is-in-the-middle-exploiting-mid
Repo
Framework

Proteomics Analysis of FLT3-ITD Mutation in Acute Myeloid Leukemia Using Deep Learning Neural Network


Title	Proteomics Analysis of FLT3-ITD Mutation in Acute Myeloid Leukemia Using Deep Learning Neural Network
Authors	Christine A. Liang, Lei Chen, Amer Wahed, Andy N. D. Nguyen
Abstract	Deep Learning can significantly benefit cancer proteomics and genomics. In this study, we attempt to determine a set of critical proteins that are associated with the FLT3-ITD mutation in newly-diagnosed acute myeloid leukemia patients. A Deep Learning network consisting of autoencoders forming a hierarchical model from which high-level features are extracted without labeled training data. Dimensional reduction reduced the number of critical proteins from 231 to 20. Deep Learning found an excellent correlation between FLT3-ITD mutation with the levels of these 20 critical proteins (accuracy 97%, sensitivity 90%, specificity 100%). Our Deep Learning network could hone in on 20 proteins with the strongest association with FLT3-ITD. The results of this study allow a novel approach to determine critical protein pathways in the FLT3-ITD mutation, and provide proof-of-concept for an accurate approach to model big data in cancer proteomics and genomics.
Tasks
Published	2017-12-29
URL	http://arxiv.org/abs/1801.01019v1
PDF	http://arxiv.org/pdf/1801.01019v1.pdf
PWC	https://paperswithcode.com/paper/proteomics-analysis-of-flt3-itd-mutation-in
Repo
Framework