October 19, 2019

2969 words 14 mins read

Paper Group ANR 334

Image reconstruction through metamorphosis. Drug Recommendation toward Safe Polypharmacy. Knowledge Graph Completion to Predict Polypharmacy Side Effects. A Multi-Biometrics for Twins Identification Based Speech and Ear. Constructing Compact Brain Connectomes for Individual Fingerprinting. Evaluating Active Learning Heuristics for Sequential Diagno …

Image reconstruction through metamorphosis


Title	Image reconstruction through metamorphosis
Authors	Gris Barbara, Chen Chong, Öktem Ozan
Abstract	This article adapts the framework of metamorphosis to solve inverse problems in imaging that includes joint reconstruction and image registration. The deformations in question have two components, one that is a geometric deformation moving intensities and the other a deformation of intensity values itself, which, e.g., allows for appearance of a new structure. The idea developed here is to reconstruct an image from noisy and indirect observations by registering, via metamorphosis, a template to the observed data. Unlike a registration with only geometrical changes, this framework gives good results when intensities of the template are poorly chosen. We show that this method is a well-defined regularisation method (proving existence, stability and convergence) and present several numerical examples.
Tasks	Image Reconstruction, Image Registration
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01225v2
PDF	http://arxiv.org/pdf/1806.01225v2.pdf
PWC	https://paperswithcode.com/paper/image-reconstruction-through-metamorphosis
Repo
Framework

Drug Recommendation toward Safe Polypharmacy


Title	Drug Recommendation toward Safe Polypharmacy
Authors	Wen-Hao Chiang, Li Shen, Lang Li, Xia Ning
Abstract	Adverse drug reactions (ADRs) induced from high-order drug-drug interactions (DDIs) due to polypharmacy represent a significant public health problem. In this paper, we formally formulate the to-avoid and safe (with respect to ADRs) drug recommendation problems when multiple drugs have been taken simultaneously. We develop a joint model with a recommendation component and an ADR label prediction component to recommend for a prescription a set of to-avoid drugs that will induce ADRs if taken together with the prescription. We also develop real drug-drug interaction datasets and corresponding evaluation protocols. Our experimental results on real datasets demonstrate the strong performance of the joint model compared to other baseline methods.
Tasks
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03185v1
PDF	http://arxiv.org/pdf/1803.03185v1.pdf
PWC	https://paperswithcode.com/paper/drug-recommendation-toward-safe-polypharmacy
Repo
Framework

Knowledge Graph Completion to Predict Polypharmacy Side Effects


Title	Knowledge Graph Completion to Predict Polypharmacy Side Effects
Authors	Brandon Malone, Alberto García-Durán, Mathias Niepert
Abstract	The polypharmacy side effect prediction problem considers cases in which two drugs taken individually do not result in a particular side effect; however, when the two drugs are taken in combination, the side effect manifests. In this work, we demonstrate that multi-relational knowledge graph completion achieves state-of-the-art results on the polypharmacy side effect prediction problem. Empirical results show that our approach is particularly effective when the protein targets of the drugs are well-characterized. In contrast to prior work, our approach provides more interpretable predictions and hypotheses for wet lab validation.
Tasks	Knowledge Graph Completion
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09227v1
PDF	http://arxiv.org/pdf/1810.09227v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-graph-completion-to-predict
Repo
Framework

A Multi-Biometrics for Twins Identification Based Speech and Ear


Title	A Multi-Biometrics for Twins Identification Based Speech and Ear
Authors	Cihan Akin, Umit Kacar, Murvet Kirci
Abstract	The development of technology biometrics becomes crucial more. To define human characteristic biometric systems are used but because of inability of traditional biometric systems to recognize twins, multimodal biometric systems are developed. In this study a multimodal biometric recognition system is proposed to recognize twins from each other and from the other people by using image and speech data. The speech or image data can be enough to recognize people from each other but twins cannot be distinguished with one of these data. Therefore a robust recognition system with the combine of speech and ear images is needed. As database, the photos and speech data of 39 twins are used. For speech recognition MFCC and DTW algorithms are used. Also, Gabor filter and DCVA algorithms are used for ear identification. Multi-biometrics success rate is increased by making matching score level fusion. Especially, rank-5 is reached 100%. We think that speech and ear can be complementary. Therefore, it is result that multi-biometrics based speech and ear is effective for human identifications.
Tasks	Speech Recognition
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09056v1
PDF	http://arxiv.org/pdf/1801.09056v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-biometrics-for-twins-identification
Repo
Framework

Constructing Compact Brain Connectomes for Individual Fingerprinting


Title	Constructing Compact Brain Connectomes for Individual Fingerprinting
Authors	Vikram Ravindra, Petros Drineas, Ananth Grama
Abstract	Recent neuroimaging studies have shown that functional connectomes are unique to individuals, i.e., two distinct fMRIs taken over different sessions of the same subject are more similar in terms of their connectomes than those from two different subjects. In this study, we present significant new results that identify, for the first time, specific parts of resting-state and task-specific connectomes that code the unique signatures. We show that a very small part of the connectome codes the signatures. A network of these features is shown to achieve excellent training and test accuracy in matching imaging datasets. We show that these features are statistically significant, robust to perturbations, invariant across populations, and are localized to a small number of structural regions of the brain. Furthermore, we show that for task-specific connectomes, the regions identified by our method are consistent with their known functional characterization. We present a new matrix sampling technique to derive computationally efficient and accurate methods for identifying the discriminating sub-connectome and support all of our claims using state-of-the-art statistical tests and computational techniques.
Tasks
Published	2018-05-22
URL	https://arxiv.org/abs/1805.08649v2
PDF	https://arxiv.org/pdf/1805.08649v2.pdf
PWC	https://paperswithcode.com/paper/constructing-compact-brain-connectomes-for
Repo
Framework

Evaluating Active Learning Heuristics for Sequential Diagnosis


Title	Evaluating Active Learning Heuristics for Sequential Diagnosis
Authors	Patrick Rodler, Wolfgang Schmid
Abstract	Given a malfunctioning system, sequential diagnosis aims at identifying the root cause of the failure in terms of abnormally behaving system components. As initial system observations usually do not suffice to deterministically pin down just one explanation of the system’s misbehavior, additional system measurements can help to differentiate between possible explanations. The goal is to restrict the space of explanations until there is only one (highly probable) explanation left. To achieve this with a minimal-cost set of measurements, various (active learning) heuristics for selecting the best next measurement have been proposed. We report preliminary results of extensive ongoing experiments with a set of selection heuristics on real-world diagnosis cases. In particular, we try to answer questions such as “Is some heuristic always superior to all others?", “On which factors does the (relative) performance of the particular heuristics depend?” or “Under which circumstances should I use which heuristic?”
Tasks	Active Learning, Sequential Diagnosis
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03083v1
PDF	http://arxiv.org/pdf/1807.03083v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-active-learning-heuristics-for
Repo
Framework

Modular Networks: Learning to Decompose Neural Computation


Title	Modular Networks: Learning to Decompose Neural Computation
Authors	Louis Kirsch, Julius Kunze, David Barber
Abstract	Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a training algorithm that flexibly chooses neural modules based on the data to be processed. Both the decomposition and modules are learned end-to-end. In contrast to existing approaches, training does not rely on regularization to enforce diversity in module use. We apply modular networks both to image recognition and language modeling tasks, where we achieve superior performance compared to several baselines. Introspection reveals that modules specialize in interpretable contexts.
Tasks	Language Modelling
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05249v1
PDF	http://arxiv.org/pdf/1811.05249v1.pdf
PWC	https://paperswithcode.com/paper/modular-networks-learning-to-decompose-neural
Repo
Framework

Automatically designing CNN architectures using genetic algorithm for image classification


Title	Automatically designing CNN architectures using genetic algorithm for image classification
Authors	Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen
Abstract	Convolutional Neural Networks (CNNs) have gained a remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For most state-of-the-art CNNs, their architectures are often manually-designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this paper, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, by comparing to the state-of-the-art peer competitors covering eight manually-designed CNNs, seven automatic+manually tuning and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually-designed and automatic+manually tuning CNNs, while consumes much less of computational resource.
Tasks	Image Classification
Published	2018-08-11
URL	https://arxiv.org/abs/1808.03818v3
PDF	https://arxiv.org/pdf/1808.03818v3.pdf
PWC	https://paperswithcode.com/paper/automatically-designing-cnn-architectures
Repo
Framework

Representation Learning in Partially Observable Environments using Sensorimotor Prediction


Title	Representation Learning in Partially Observable Environments using Sensorimotor Prediction
Authors	Thibaut Kulak, Michael Garcia Ortiz
Abstract	In order to explore and act autonomously in an environment, an agent needs to learn from the sensorimotor information that is captured while acting. By extracting the regularities in this sensorimotor stream, it can learn a model of the world, which in turn can be used as a basis for action and exploration. This requires the acquisition of compact representations from a possibly high dimensional raw observation, which is noisy and ambiguous. In this paper, we learn sensory representations from sensorimotor prediction. We propose a model which integrates sensorimotor information over time, and project it in a sensory representation which is useful for prediction. We emphasize on a simple example the role of motor and memory for learning sensory representations.
Tasks	Representation Learning
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00268v2
PDF	http://arxiv.org/pdf/1803.00268v2.pdf
PWC	https://paperswithcode.com/paper/representation-learning-in-partially
Repo
Framework

Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals


Title	Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals
Authors	Soumitro Chakrabarty, Emanuël A. P. Habets
Abstract	Supervised learning based methods for source localization, being data driven, can be adapted to different acoustic conditions via training and have been shown to be robust to adverse acoustic environments. In this paper, a convolutional neural network (CNN) based supervised learning method for estimating the direction-of-arrival (DOA) of multiple speakers is proposed. Multi-speaker DOA estimation is formulated as a multi-class multi-label classification problem, where the assignment of each DOA label to the input feature is treated as a separate binary classification problem. The phase component of the short-time Fourier transform (STFT) coefficients of the received microphone signals are directly fed into the CNN, and the features for DOA estimation are learnt during training. Utilizing the assumption of disjoint speaker activity in the STFT domain, a novel method is proposed to train the CNN with synthesized noise signals. Through experimental evaluation with both simulated and measured acoustic impulse responses, the ability of the proposed DOA estimation approach to adapt to unseen acoustic conditions and its robustness to unseen noise type is demonstrated. Through additional empirical investigation, it is also shown that with an array of M microphones our proposed framework yields the best localization performance with M-1 convolution layers. The ability of the proposed method to accurately localize speakers in a dynamic acoustic scenario with varying number of sources is also shown.
Tasks	Multi-Label Classification
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11722v1
PDF	http://arxiv.org/pdf/1807.11722v1.pdf
PWC	https://paperswithcode.com/paper/multi-speaker-doa-estimation-using-deep
Repo
Framework

Automated design of collective variables using supervised machine learning


Title	Automated design of collective variables using supervised machine learning
Authors	Mohammad M. Sultan, Vijay S. Pande
Abstract	Selection of appropriate collective variables for enhancing sampling of molecular simulations remains an unsolved problem in computational biophysics. In particular, picking initial collective variables (CVs) is particularly challenging in higher dimensions. Which atomic coordinates or transforms there of from a list of thousands should one pick for enhanced sampling runs? How does a modeler even begin to pick starting coordinates for investigation? This remains true even in the case of simple two state systems and only increases in difficulty for multi-state systems. In this work, we solve the initial CV problem using a data-driven approach inspired by the filed of supervised machine learning. In particular, we show how the decision functions in supervised machine learning (SML) algorithms can be used as initial CVs (SML_cv) for accelerated sampling. Using solvated alanine dipeptide and Chignolin mini-protein as our test cases, we illustrate how the distance to the Support Vector Machines’ decision hyperplane, the output probability estimates from Logistic Regression, the outputs from deep neural network classifiers, and other classifiers may be used to reversibly sample slow structural transitions. We discuss the utility of other SML algorithms that might be useful for identifying CVs for accelerating molecular simulations.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10510v2
PDF	http://arxiv.org/pdf/1802.10510v2.pdf
PWC	https://paperswithcode.com/paper/automated-design-of-collective-variables
Repo
Framework

An Ontology-Based Artificial Intelligence Model for Medicine Side-Effect Prediction: Taking Traditional Chinese Medicine as An Example


Title	An Ontology-Based Artificial Intelligence Model for Medicine Side-Effect Prediction: Taking Traditional Chinese Medicine as An Example
Authors	Yuanzhe Yao, Zeheng Wang, Liang Li, Kun Lu, Runyu Liu, Zhiyuan Liu, Jing Yan
Abstract	In this work, an ontology-based model for AI-assisted medicine side-effect (SE) prediction is developed, where three main components, including the drug model, the treatment model, and the AI-assisted prediction model, of proposed model are presented. To validate the proposed model, an ANN structure is established and trained by two hundred and forty-two TCM prescriptions. These data are gathered and classified from the most famous ancient TCM book and more than one thousand SE reports, in which two ontology-based attributions, hot and cold, are introduced to evaluate whether the prescription will cause SE or not. The results preliminarily reveal that it is a relationship between the ontology-based attributions and the corresponding predicted indicator that can be learnt by AI for predicting the SE, which suggests the proposed model has a potential in AI-assisted SE prediction. However, it should be noted that, the proposed model highly depends on the sufficient clinic data, and hereby, much deeper exploration is important for enhancing the accuracy of the prediction.
Tasks
Published	2018-09-12
URL	https://arxiv.org/abs/1809.04258v3
PDF	https://arxiv.org/pdf/1809.04258v3.pdf
PWC	https://paperswithcode.com/paper/an-ontology-based-artificial-intelligence
Repo
Framework

Deep Learning Approach for Building Detection in Satellite Multispectral Imagery


Title	Deep Learning Approach for Building Detection in Satellite Multispectral Imagery
Authors	Geesara Prathap, Ilya Afanasyev
Abstract	Building detection from satellite multispectral imagery data is being a fundamental but a challenging problem mainly because it requires correct recovery of building footprints from high-resolution images. In this work, we propose a deep learning approach for building detection by applying numerous enhancements throughout the process. Initial dataset is preprocessed by 2-sigma percentile normalization. Then data preparation includes ensemble modelling where 3 models were created while incorporating OpenStreetMap data. Binary Distance Transformation (BDT) is used for improving data labeling process and the U-Net (Convolutional Networks for Biomedical Image Segmentation) is modified by adding batch normalization wrappers. Afterwards, it is explained how each component of our approach is correlated with the final detection accuracy. Finally, we compare our results with winning solutions of SpaceNet 2 competition for real satellite multispectral images of Vegas, Paris, Shanghai and Khartoum, demonstrating the importance of our solution for achieving higher building detection accuracy.
Tasks	Semantic Segmentation
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04247v1
PDF	http://arxiv.org/pdf/1811.04247v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-approach-for-building-detection
Repo
Framework

Joint Coarse-And-Fine Reasoning for Deep Optical Flow


Title	Joint Coarse-And-Fine Reasoning for Deep Optical Flow
Authors	Victor Vaquero, German Ros, Francesc Moreno-Noguer, Antonio M. Lopez, Alberto Sanfeliu
Abstract	We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.
Tasks	Optical Flow Estimation
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07416v1
PDF	http://arxiv.org/pdf/1808.07416v1.pdf
PWC	https://paperswithcode.com/paper/joint-coarse-and-fine-reasoning-for-deep
Repo
Framework

Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learning


Title	Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learning
Authors	Mattia G. Bergomi, Patrizio Frosini, Daniela Giorgi, Nicola Quercioli
Abstract	The aim of this paper is to provide a general mathematical framework for group equivariance in the machine learning context. The framework builds on a synergy between persistent homology and the theory of group actions. We define group-equivariant non-expansive operators (GENEOs), which are maps between function spaces associated with groups of transformations. We study the topological and metric properties of the space of GENEOs to evaluate their approximating power and set the basis for general strategies to initialise and compose operators. We begin by defining suitable pseudo-metrics for the function spaces, the equivariance groups, and the set of non-expansive operators. Basing on these pseudo-metrics, we prove that the space of GENEOs is compact and convex, under the assumption that the function spaces are compact and convex. These results provide fundamental guarantees in a machine learning perspective. We show examples on the MNIST and fashion-MNIST datasets. By considering isometry-equivariant non-expansive operators, we describe a simple strategy to select and sample operators, and show how the selected and sampled operators can be used to perform both classical metric learning and an effective initialisation of the kernels of a convolutional neural network.
Tasks	Metric Learning
Published	2018-12-31
URL	http://arxiv.org/abs/1812.11832v3
PDF	http://arxiv.org/pdf/1812.11832v3.pdf
PWC	https://paperswithcode.com/paper/towards-a-topological-geometrical-theory-of
Repo
Framework