October 20, 2019

2978 words 14 mins read

Paper Group ANR 29

CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients. Low-Cost Recurrent Neural Network Expected Performance Evaluation. When logic lays down the law. Linear-Time Constituency Parsing with RNNs and Dynamic Programming. Iris Recognition with a Database of Iris Images Obtained in Visible Light Using Smartphon …

CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients


Title	CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients
Authors	Zeyuan Wang, Josiah Poon, Shiding Sun, Simon Poon
Abstract	Syndrome differentiation in Traditional Chinese Medicine (TCM) is the process of understanding and reasoning body condition, which is the essential step and premise of effective treatments. However, due to its complexity and lack of standardization, it is challenging to achieve. In this study, we consider each patient’s record as a one-dimensional image and symptoms as pixels, in which missing and negative values are represented by zero pixels. The objective is to find relevant symptoms first and then map them to proper syndromes, that is similar to the object detection problem in computer vision. Inspired from it, we employ multi-instance multi-task learning combined with the convolutional neural network (MIMT-CNN) for syndrome differentiation, which takes region proposals as input and output image labels directly. The neural network consists of region proposals generation, convolutional layer, fully connected layer, and max pooling (multi-instance pooling) layer followed by the sigmoid function in each syndrome prediction task for image representation learning and final results generation. On the diabetes dataset, it performs better than all other baseline methods. Moreover, it shows stability and reliability to generate results, even on the dataset with small sample size, a large number of missing values and noises.
Tasks	Multi-Task Learning, Object Detection, Representation Learning
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07764v2
PDF	http://arxiv.org/pdf/1812.07764v2.pdf
PWC	https://paperswithcode.com/paper/cnn-based-multi-instance-multi-task-learning
Repo
Framework

Low-Cost Recurrent Neural Network Expected Performance Evaluation


Title	Low-Cost Recurrent Neural Network Expected Performance Evaluation
Authors	Andrés Camero, Jamal Toutouh, Enrique Alba
Abstract	Recurrent neural networks are a powerful tool, but they are very sensitive to their hyper-parameter configuration. Moreover, training properly a recurrent neural network is a tough task, therefore selecting an appropriate configuration is critical. Varied strategies have been proposed to tackle this issue. However, most of them are still impractical because of the time/resources needed. In this study, we propose a low computational cost model to evaluate the expected performance of a given architecture based on the distribution of the error of random samples of the weights. We empirically validate our proposal using three use cases. The results suggest that this is a promising alternative to reduce the cost of exploration for hyper-parameter optimization.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07159v2
PDF	http://arxiv.org/pdf/1805.07159v2.pdf
PWC	https://paperswithcode.com/paper/low-cost-recurrent-neural-network-expected
Repo
Framework

When logic lays down the law


Title	When logic lays down the law
Authors	Bjørn Jespersen, Ana de Almeida Borges, Jorge del Castillo Tierz, Juan José Conejero Rodríguez, Eric Sancho Adamson, Aleix Solé Sánchez, Nika Pona, Joost J. Joosten
Abstract	We analyse so-called computable laws, i.e., laws that can be enforced by automatic procedures. These laws should be logically perfect and unambiguous, but sometimes they are not. We use a regulation on road transport to illustrate this issue, and show what some fragments of this regulation would look like if rewritten in the image of logic. We further propose desiderata to be fulfilled by computable laws, and provide a critical platform from which to assess existing laws and a guideline for composing future ones.
Tasks
Published	2018-10-06
URL	http://arxiv.org/abs/1810.03002v1
PDF	http://arxiv.org/pdf/1810.03002v1.pdf
PWC	https://paperswithcode.com/paper/when-logic-lays-down-the-law
Repo
Framework

Linear-Time Constituency Parsing with RNNs and Dynamic Programming


Title	Linear-Time Constituency Parsing with RNNs and Dynamic Programming
Authors	Juneki Hong, Liang Huang
Abstract	Recently, span-based constituency parsing has achieved competitive accuracies with extremely simple models by using bidirectional RNNs to model “spans”. However, the minimal span parser of Stern et al (2017a) which holds the current state of the art accuracy is a chart parser running in cubic time, $O(n^3)$, which is too slow for longer sentences and for applications beyond sentence boundaries such as end-to-end discourse parsing and joint sentence boundary detection and parsing. We propose a linear-time constituency parser with RNNs and dynamic programming using graph-structured stack and beam search, which runs in time $O(n b^2)$ where $b$ is the beam size. We further speed this up to $O(n b\log b)$ by integrating cube pruning. Compared with chart parsing baselines, this linear-time parser is substantially faster for long sentences on the Penn Treebank and orders of magnitude faster for discourse parsing, and achieves the highest F1 accuracy on the Penn Treebank among single model end-to-end systems.
Tasks	Boundary Detection, Constituency Parsing
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06995v2
PDF	http://arxiv.org/pdf/1805.06995v2.pdf
PWC	https://paperswithcode.com/paper/linear-time-constituency-parsing-with-rnns
Repo
Framework

Iris Recognition with a Database of Iris Images Obtained in Visible Light Using Smartphone Camera


Title	Iris Recognition with a Database of Iris Images Obtained in Visible Light Using Smartphone Camera
Authors	Mateusz Trokielewicz
Abstract	This paper delivers a new database of iris images collected in visible light using a mobile phone’s camera and presents results of experiments involving existing commercial and open-source iris recognition methods, namely: IriCore, VeriEye, MIRLIN and OSIRIS. Several important observations are made. First, we manage to show that after simple preprocessing, such images offer good visibility of iris texture even in heavily-pigmented irides. Second, for all four methods, the enrollment stage is not much affected by the fact that different type of data is used as input. This translates to zero or close-to-zero Failure To Enroll, i.e., cases when templates could not be extracted from the samples. Third, we achieved good matching accuracy, with correct genuine match rate exceeding 94.5% for all four methods, while simultaneously being able to maintain zero false match rate in every case. Correct genuine match rate of over 99.5% was achieved using one of the commercial methods, showing that such images can be used with the existing biometric solutions with minimum additional effort required. Finally, the experiments revealed that incorrect image segmentation is the most prevalent cause of recognition accuracy decrease. To our best knowledge, this is the first database of iris images captured using a mobile device, in which image quality exceeds this of a near-infrared illuminated iris images, as defined in ISO/IEC 19794-6 and 29794-6 documents. This database will be publicly available to all researchers.
Tasks	Iris Recognition, Semantic Segmentation
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00214v1
PDF	http://arxiv.org/pdf/1809.00214v1.pdf
PWC	https://paperswithcode.com/paper/iris-recognition-with-a-database-of-iris
Repo
Framework

Topographic Representation for Quantum Machine Learning


Title	Topographic Representation for Quantum Machine Learning
Authors	Bruce MacLennan
Abstract	This paper proposes a brain-inspired approach to quantum machine learning with the goal of circumventing many of the complications of other approaches. The fact that quantum processes are unitary presents both opportunities and challenges. A principal opportunity is that a large number of computations can be carried out in parallel in linear superposition, that is, quantum parallelism. The challenge is that the process is linear, and most approaches to machine learning depend significantly on nonlinear processes. Fortunately, the situation is not hopeless, for we know that nonlinear processes can be embedded in unitary processes, as is familiar from the circuit model of quantum computation. This paper explores an approach to the quantum implementation of machine learning involving nonlinear functions operating on information represented topographically (by computational maps), as common in neural cortex.
Tasks	Quantum Machine Learning
Published	2018-10-13
URL	https://arxiv.org/abs/1810.06992v3
PDF	https://arxiv.org/pdf/1810.06992v3.pdf
PWC	https://paperswithcode.com/paper/topographic-representation-for-quantum
Repo
Framework

RDF2Vec-based Classification of Ontology Alignment Changes


Title	RDF2Vec-based Classification of Ontology Alignment Changes
Authors	Matthias Jurisch, Bodo Igler
Abstract	When ontologies cover overlapping topics, the overlap can be represented using ontology alignments. These alignments need to be continuously adapted to changing ontologies. Especially for large ontologies this is a costly task often consisting of manual work. Finding changes that do not lead to an adaption of the alignment can potentially make this process significantly easier. This work presents an approach to finding these changes based on RDF embeddings and common classification techniques. To examine the feasibility of this approach, an evaluation on a real-world dataset is presented. In this evaluation, the best classifiers reached a precision of 0.8.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09145v1
PDF	http://arxiv.org/pdf/1805.09145v1.pdf
PWC	https://paperswithcode.com/paper/rdf2vec-based-classification-of-ontology
Repo
Framework

Computing FO-Rewritings in EL in Practice: from Atomic to Conjunctive Queries


Title	Computing FO-Rewritings in EL in Practice: from Atomic to Conjunctive Queries
Authors	Peter Hansen, Carsten Lutz
Abstract	A prominent approach to implementing ontology-mediated queries (OMQs) is to rewrite into a first-order query, which is then executed using a conventional SQL database system. We consider the case where the ontology is formulated in the description logic EL and the actual query is a conjunctive query and show that rewritings of such OMQs can be efficiently computed in practice, in a sound and complete way. Our approach combines a reduction with a decomposed backwards chaining algorithm for OMQs that are based on the simpler atomic queries, also illuminating the relationship between first-order rewritings of OMQs based on conjunctive and on atomic queries. Experiments with real-world ontologies show promising results.
Tasks
Published	2018-04-18
URL	http://arxiv.org/abs/1804.06907v1
PDF	http://arxiv.org/pdf/1804.06907v1.pdf
PWC	https://paperswithcode.com/paper/computing-fo-rewritings-in-el-in-practice
Repo
Framework

Predicting citation counts based on deep neural network learning techniques


Title	Predicting citation counts based on deep neural network learning techniques
Authors	Ali Abrishami, Sadegh Aliakbary
Abstract	With the growing number of published scientific papers world-wide, the need to evaluation and quality assessment methods for research papers is increasing. Scientific fields such as scientometrics, informetrics and bibliometrics establish quantified analysis methods and measurements for scientific papers. In this area, an important problem is to predict the future influence of a published paper. Particularly, early discrimination between influential papers and insignificant papers may find important applications. In this regard, one of the most important metrics is the number of citations to the paper, since this metric is widely utilized in the evaluation of scientific publications and moreover, it serves as the basis for many other metrics such as h-index. In this paper, we propose a novel method for predicting long-term citations of a paper based on the number of its citations in the first few years after publication. In order to train a citations prediction model, we employed artificial neural networks which is a powerful machine learning tool with recently growing applications in many domains including image and text processing. The empirical experiments show that our proposed method out-performs state-of-the-art methods with respect to the prediction accuracy in both yearly and total prediction of the number of citations.
Tasks
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04365v3
PDF	http://arxiv.org/pdf/1809.04365v3.pdf
PWC	https://paperswithcode.com/paper/nncp-a-citation-count-prediction-methodology
Repo
Framework

Lessons from the Bible on Modern Topics: Low-Resource Multilingual Topic Model Evaluation


Title	Lessons from the Bible on Modern Topics: Low-Resource Multilingual Topic Model Evaluation
Authors	Shudong Hao, Jordan Boyd-Graber, Michael J. Paul
Abstract	Multilingual topic models enable document analysis across languages through coherent multilingual summaries of the data. However, there is no standard and effective metric to evaluate the quality of multilingual topics. We introduce a new intrinsic evaluation of multilingual topic models that correlates well with human judgments of multilingual topic coherence as well as performance in downstream applications. Importantly, we also study evaluation for low-resource languages. Because standard metrics fail to accurately measure topic quality when robust external resources are unavailable, we propose an adaptation model that improves the accuracy and reliability of these metrics in low-resource settings.
Tasks	Topic Models
Published	2018-04-26
URL	http://arxiv.org/abs/1804.10184v1
PDF	http://arxiv.org/pdf/1804.10184v1.pdf
PWC	https://paperswithcode.com/paper/lessons-from-the-bible-on-modern-topics-low
Repo
Framework

Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop


Title	Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
Authors	Martin Biehl, Christian Guckelsberger, Christoph Salge, Simón C. Smith, Daniel Polani
Abstract	Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g.\ different environments or agent morphologies. In the literature, paradigms that share this independence have been summarised under the notion of intrinsic motivations. In general and in contrast to active inference, these models of motivation come without a commitment to particular inference and action selection mechanisms. In this article, we study if the inference and action selection machinery of active inference can also be used by alternatives to the originally included intrinsic motivation. The perception-action loop explicitly relates inference and action selection to the environment and agent memory, and is consequently used as foundation for our analysis. We reconstruct the active inference approach, locate the original formulation within, and show how alternative intrinsic motivations can be used while keeping many of the original features intact. Furthermore, we illustrate the connection to universal reinforcement learning by means of our formalism. Active inference research may profit from comparisons of the dynamics induced by alternative intrinsic motivations. Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.
Tasks
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08083v1
PDF	http://arxiv.org/pdf/1806.08083v1.pdf
PWC	https://paperswithcode.com/paper/expanding-the-active-inference-landscape-more
Repo
Framework

Wireless Multi-Sensor Networks for Smart Cities: A Prototype System with Statistical Data Analysis


Title	Wireless Multi-Sensor Networks for Smart Cities: A Prototype System with Statistical Data Analysis
Authors	Balázs Csanád Csáji, Zsolt Kemény, Gianfranco Pedone, András Kuti, József Váncza
Abstract	As urbanization proceeds at an astonishing rate, cities have to continuously improve their solutions that affect the safety, health and overall wellbeing of their residents. Smart city projects worldwide build on advanced sensor, information and communication technologies to help dealing with issues like air pollution, waste management, traffic optimization, and energy efficiency. The paper reports about the prototype of a smart city initiative in Budapest which applies various sensors installed on the public lighting system and a cloud-based analytical module. While the installed wireless multi-sensor network gathers information about a number of stressors, the module integrates and statistically processes the data. The module can handle inconsistent, missing and noisy data and can extrapolate the measurements in time and space, namely, it can create short-term forecasts and smoothed maps, both accompanied by reliability estimates. The resulting database uses geometric representations and can serve as an information centre for public services.
Tasks
Published	2018-07-20
URL	http://arxiv.org/abs/1807.07818v1
PDF	http://arxiv.org/pdf/1807.07818v1.pdf
PWC	https://paperswithcode.com/paper/wireless-multi-sensor-networks-for-smart
Repo
Framework

Global Transition-based Non-projective Dependency Parsing


Title	Global Transition-based Non-projective Dependency Parsing
Authors	Carlos Gómez-Rodríguez, Tianze Shi, Lillian Lee
Abstract	Shi, Huang, and Lee (2017) obtained state-of-the-art results for English and Chinese dependency parsing by combining dynamic-programming implementations of transition-based dependency parsers with a minimal set of bidirectional LSTM features. However, their results were limited to projective parsing. In this paper, we extend their approach to support non-projectivity by providing the first practical implementation of the MH_4 algorithm, an $O(n^4)$ mildly nonprojective dynamic-programming parser with very high coverage on non-projective treebanks. To make MH_4 compatible with minimal transition-based feature sets, we introduce a transition-based interpretation of it in which parser items are mapped to sequences of transitions. We thus obtain the first implementation of global decoding for non-projective transition-based parsing, and demonstrate empirically that it is more effective than its projective counterpart in parsing a number of highly non-projective languages
Tasks	Dependency Parsing
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01745v1
PDF	http://arxiv.org/pdf/1807.01745v1.pdf
PWC	https://paperswithcode.com/paper/global-transition-based-non-projective
Repo
Framework

AceKG: A Large-scale Knowledge Graph for Academic Data Mining


Title	AceKG: A Large-scale Knowledge Graph for Academic Data Mining
Authors	Ruijie Wang, Yuchen Yan, Jialu Wang, Yuting Jia, Ye Zhang, Weinan Zhang, Xinbing Wang
Abstract	Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing. In this paper, we present AceKG, a new large-scale KG in academic domain. AceKG not only provides clean academic information, but also offers a large-scale benchmark dataset for researchers to conduct challenging data mining projects including link prediction, community detection and scholar classification. Specifically, AceKG describes 3.13 billion triples of academic facts based on a consistent ontology, including necessary properties of papers, authors, fields of study, venues and institutes, as well as the relations among them. To enrich the proposed knowledge graph, we also perform entity alignment with existing databases and rule-based inference. Based on AceKG, we conduct experiments of three typical academic data mining tasks and evaluate several state-of- the-art knowledge embedding and network representation learning approaches on the benchmark datasets built from AceKG. Finally, we discuss several promising research directions that benefit from AceKG.
Tasks	Community Detection, Entity Alignment, Knowledge Graphs, Link Prediction, Representation Learning
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08484v2
PDF	http://arxiv.org/pdf/1807.08484v2.pdf
PWC	https://paperswithcode.com/paper/acekg-a-large-scale-knowledge-graph-for
Repo
Framework

Robust Tumor Localization with Pyramid Grad-CAM


Title	Robust Tumor Localization with Pyramid Grad-CAM
Authors	Sungmin Lee, Jangho Lee, Jungbeom Lee, Chul-Kee Park, Sungroh Yoon
Abstract	A meningioma is a type of brain tumor that requires tumor volume size follow ups in order to reach appropriate clinical decisions. A fully automated tool for meningioma detection is necessary for reliable and consistent tumor surveillance. There have been various studies concerning automated lesion detection. Studies on the application of convolutional neural network (CNN)-based methods, which have achieved a state-of-the-art level of performance in various computer vision tasks, have been carried out. However, the applicable diseases are limited, owing to a lack of strongly annotated data being present in medical image analysis. In order to resolve the above issue we propose pyramid gradient-based class activation mapping (PG-CAM) which is a novel method for tumor localization that can be trained in weakly supervised manner. PG-CAM uses a densely connected encoder-decoder-based feature pyramid network (DC-FPN) as a backbone structure, and extracts a multi-scale Grad-CAM that captures hierarchical features of a tumor. We tested our model using meningioma brain magnetic resonance (MR) data collected from the collaborating hospital. In our experiments, PG-CAM outperformed Grad-CAM by delivering a 23 percent higher localization accuracy for the validation set.
Tasks
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11393v1
PDF	http://arxiv.org/pdf/1805.11393v1.pdf
PWC	https://paperswithcode.com/paper/robust-tumor-localization-with-pyramid-grad
Repo
Framework