Latest in

total 8907took 0.34s
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven ApproachesFeb 12 2018Healthcare companies must submit pharmaceutical drugs or medical devices to regulatory bodies before marketing new technology. Regulatory bodies frequently require transparent and interpretable computational modelling to justify a new healthcare technology, ... More
Bayesian inference for bivariate ranksFeb 09 2018A recommender system based on ranks is proposed, where an expert's ranking of a set of objects and a user's ranking of a subset of those objects are combined to make a prediction of the user's ranking of all objects. The rankings are assumed to be induced ... More
Statistical Learnability of Generalized Additive Models based on Total Variation RegularizationFeb 08 2018A generalized additive model (GAM, Hastie and Tibshirani (1987)) is a nonparametric model by the sum of univariate functions with respect to each explanatory variable, i.e., $f({\mathbf x}) = \sum f_j(x_j)$, where $x_j\in\mathbb{R}$ is $j$-th component ... More
Learning Sparse Wavelet RepresentationsFeb 08 2018In this work we propose a method for learning wavelet filters directly from data. We accomplish this by framing the discrete wavelet transform as a modified convolutional neural network. We introduce an autoencoder wavelet transform network that is trained ... More
State Compression of Markov Processes via Empirical Low-Rank EstimationFeb 08 2018Model reduction is a central problem in analyzing complex systems and high-dimensional data. We study the state compression of finite-state Markov process from its empirical trajectories. We adopt a low-rank model which is motivated by the state aggregation ... More
Online Decomposition of Compressive Streaming Data Using $n$-$\ell_1$ Cluster-Weighted MinimizationFeb 08 2018We consider a decomposition method for compressive streaming data in the context of online compressive Robust Principle Component Analysis (RPCA). The proposed decomposition solves an $n$-$\ell_1$ cluster-weighted minimization to decompose a sequence ... More
Multivariate Study of the Star Formation Rate in Galaxies: Bimodality RevisitedFeb 08 2018Subjective classification of galaxies can mislead us in the quest of the origin regarding formation and evolution of galaxies. Multivariate analyses are the best tools used for such kind of purpose to better understand the differences between various ... More
mGPfusion: Predicting protein stability changes with Gaussian process kernel learning and data fusionFeb 08 2018Proteins are commonly used by biochemical industry for numerous processes. Refining these proteins' properties via mutations causes stability effects as well. Accurate computational method to predict how mutations affect protein stability are necessary ... More
Neural Network Renormalization GroupFeb 08 2018We present a variational renormalization group approach using deep generative model composed of bijectors. The model can learn hierarchical transformations between physical variables and renormalized collective variables. It can directly generate statistically ... More
Transductive Adversarial Networks (TAN)Feb 08 2018Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily ... More
Geometry Score: A Method For Comparing Generative Adversarial NetworksFeb 07 2018One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance of a GAN by ... More
Gradient conjugate priors and deep neural networksFeb 07 2018The paper deals with learning the probability distribution of the observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian ... More
Recognition of Acoustic Events Using Masked Conditional Neural NetworksFeb 07 2018Automatic feature extraction using neural networks has accomplished remarkable success for images, but for sound recognition, these models are usually modified to fit the nature of the multi-dimensional temporal representation of the audio signal in spectrograms. ... More
Applying Cooperative Machine Learning to Speed Up the Annotation of Social Signals in Large Multi-modal CorporaFeb 07 2018Scientific disciplines, such as Behavioural Psychology, Anthropology and recently Social Signal Processing are concerned with the systematic exploration of human behaviour. A typical work-flow includes the manual annotation (also called coding) of social ... More
Intentional control of type I error over unconscious data distortion: a Neyman-Pearson classification approachFeb 07 2018The rise of social media enables millions of citizens to generate information on sensitive political issues and social events, which is scarce in authoritarian countries and is tremendously valuable for surveillance and social studies. In the enormous ... More
Sparse Linear Discriminant Analysis under the Neyman-Pearson ParadigmFeb 07 2018In contrast to the classical binary classification paradigm that minimizes the overall classification error, the Neyman-Pearson (NP) paradigm seeks classifiers with a minimal type II error while having a constrained type I error under a user-specified ... More
A Game-Theoretic Approach to Design Secure and Resilient Distributed Support Vector MachinesFeb 07 2018Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are ... More
Semi-Amortized Variational AutoencodersFeb 07 2018Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests ... More
Learning One Convolutional Layer with Overlapping PatchesFeb 07 2018We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches. Additionally, our algorithm requires only mild conditions on the underlying distribution. ... More
Yes, but Did It Work?: Evaluating Variational InferenceFeb 07 2018While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation". We propose two diagnostic algorithms to alleviate this problem. The Pareto-smoothed importance ... More
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk PredictionFeb 07 2018We train and validate a semi-supervised, multi-task LSTM on 57,675 person-weeks of data from off-the-shelf wearable heart rate sensors, showing high accuracy at detecting multiple medical conditions, including diabetes (0.8451), high cholesterol (0.7441), ... More
Cadre Modeling: Simultaneously Discovering Subpopulations and Predictive ModelsFeb 07 2018We consider the problem in regression analysis of identifying subpopulations that exhibit different patterns of response, where each subpopulation requires a different underlying model. Unlike statistical cohorts, these subpopulations are not known a ... More
Spectral Learning of Binomial HMMs for DNA Methylation DataFeb 07 2018We consider learning parameters of Binomial Hidden Markov Models, which may be used to model DNA methylation data. The standard algorithm for the problem is EM, which is computationally expensive for sequences of the scale of the mammalian genome. Recently ... More
Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial NetworksFeb 07 2018The training of Generative Adversarial Networks is a difficult task mainly due to the nature of the networks. One such issue is when the generator and discriminator start oscillating, rather than converging to a fixed point. Another case can be when one ... More
Multi-View Bayesian Correlated Component AnalysisFeb 07 2018Correlated component analysis as proposed by Dmochowski et al. (2012) is a tool for investigating brain process similarity in the responses to multiple views of a given stimulus. Correlated components are identified under the assumption that the involved ... More
Spectral Image Visualization Using Generative Adversarial NetworksFeb 07 2018Spectral images captured by satellites and radio-telescopes are analyzed to obtain information about geological compositions distributions, distant asters as well as undersea terrain. Spectral images usually contain tens to hundreds of continuous narrow ... More
Learning Role-based Graph EmbeddingsFeb 07 2018Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs ... More
Scalable Meta-Learning for Bayesian OptimizationFeb 06 2018Bayesian optimization has become a standard technique for hyperparameter optimization, including data-intensive models such as deep neural networks that may take days or weeks to train. We consider the setting where previous optimization runs are available, ... More
How to Make Causal Inferences Using TextsFeb 06 2018New text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories of interest from large collections of text. We introduce a conceptual framework for making causal inferences ... More
DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary SupervisionFeb 06 2018Estimating the travel time of a path is of great importance to smart urban mobility. Existing approaches are either based on estimating the time cost of each road segment which are not able to capture many cross-segment complex factors, or designed heuristically ... More
Near-Optimal Coresets of Kernel Density EstimatesFeb 06 2018We construct near-optimal coresets for kernel density estimate for points in $\mathbb{R^d}$ when the kernel is positive definite. Specifically we show a polynomial time construction for a coreset of size $O(\sqrt{d\log (1/\epsilon)}/\epsilon)$, and we ... More
An Occluded Stacked Hourglass Approach to Facial Landmark Localization and Occlusion EstimationFeb 05 2018A key step to driver safety is to observe the driver's activities with the face being a key step in this process to extracting information such as head pose, blink rate, yawns, talking to passenger which can then help derive higher level information such ... More
Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong ConvexityFeb 05 2018We consider the convex-concave saddle point problem $\min_{x}\max_{y} f(x)+y^\top A x-g(y)$ where $f$ is smooth and convex and $g$ is smooth and strongly convex. We prove that if the coupling matrix $A$ has full column rank, the vanilla primal-dual gradient ... More
Image restoration with generalized Gaussian mixture model patch priorsFeb 05 2018Patch priors have became an important component of image restoration. A powerful approach in this category of restoration algorithms is the popular Expected Patch Log-likelihood (EPLL) algorithm. EPLL uses a Gaussian mixture model (GMM) prior learned ... More
Information Assisted Dictionary Learning for fMRI data analysisFeb 05 2018Extracting information from functional magnetic resonance images (fMRI) has been a major area of research for many years, but is still demanding more accurate techniques. Nowadays, we have a plenty of available information about the brain-behavior that ... More
Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision SurfacesFeb 05 2018Both neural networks and decision trees are popular machine learning methods and are widely used to solve problems from diverse domains. These two classifiers are commonly used base classifiers in an ensemble framework. In this paper, we first present ... More
Non-Gaussian information from weak lensing data via deep learningFeb 04 2018Feb 06 2018Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and ... More
Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain FeaturesFeb 04 2018Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal ... More
On the Minimax Misclassification Ratio of Hypergraph Community DetectionFeb 03 2018Community detection in hypergraphs is explored. Under a generative hypergraph model called "d-wise hypergraph stochastic block model" (d-hSBM) which naturally extends the Stochastic Block Model from graphs to d-uniform hypergraphs, the asymptotic minimax ... More
A Generative Model for Natural Sounds Based on Latent Force ModellingFeb 02 2018Recent advances in analysis of subband amplitude envelopes of natural sounds have resulted in convincing synthesis, showing subband amplitudes to be a crucial component of perception. Probabilistic latent variable analysis is particularly revealing, but ... More
Scalable Lévy Process Priors for Spectral Kernel LearningFeb 02 2018Gaussian processes are rich distributions over functions, with generalization properties determined by a kernel function. When used for long-range extrapolation, predictions are particularly sensitive to the choice of kernel parameters. It is therefore ... More
Sensitivity Sampling Over Dynamic Geometric Data Streams with Applications to $k$-ClusteringFeb 01 2018Sensitivity based sampling is crucial for constructing nearly-optimal coreset for $k$-means / median clustering. In this paper, we provide a novel data structure that enables sensitivity sampling over a dynamic data stream, where points from a high dimensional ... More
On the Topic of JetsJan 31 2018We introduce jet topics: a framework to identify underlying classes of jets from collider data. Because of a close mathematical relationship between distributions of observables in jets and emergent themes in sets of documents, we can apply recent techniques ... More
Kernel Distillation for Gaussian ProcessesJan 31 2018Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature. However, the usage of GPs in real-world application is limited due to their high computational cost at inference ... More
Learning to Classify from Impure SamplesJan 30 2018A persistent challenge in practical classification tasks is that labelled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most features of data, ... More
Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operatorJan 30 2018We study the convergence of the graph Laplacian of a random geometric graph generated by an i.i.d. sample from a $m$-dimensional submanifold $M$ in $R^d$ as the sample size $n$ increases and the neighborhood size $h$ tends to zero. We show that eigenvalues ... More
Cardiac Arrhythmia Detection from ECG Combining Convolutional and Long Short-Term Memory NetworksJan 30 2018Objectives: Atrial fibrillation (AF) is a common heart rhythm disorder associated with deadly and debilitating consequences including heart failure, stroke, poor mental health, reduced quality of life and death. Having an automatic system that diagnoses ... More
Over-representation of Extreme Events in Decision-Making: A Rational Metacognitive AccountJan 30 2018The Availability bias, manifested in the over-representation of extreme eventualities in decision-making, is a well-known cognitive bias, and is generally taken as evidence of human irrationality. In this work, we present the first rational, metacognitive ... More
Mixture Proportion Estimation for Positive--Unlabeled Learning via Classifier Dimension ReductionJan 30 2018Jan 31 2018Positive--unlabeled (PU) learning considers two samples, a positive set $P$ with observations from only one class and an unlabeled set $U$ with observations from two classes. The goal is to classify observations in $U$. Class mixture proportion estimation ... More
Transformation Autoregressive NetworksJan 30 2018Jan 31 2018The fundamental task of general density estimation has been of keen interest to machine learning. Recent advances in density estimation have either: a) proposed a flexible model to estimate the conditional factors of the chain rule, $p(x_{i}\, |\, x_{i-1}, ... More
Nonlinear Dimensionality Reduction on GraphsJan 29 2018In this era of data deluge, many signal processing and machine learning tasks are faced with high-dimensional datasets, including images, videos, as well as time series generated from social, commercial and brain network interactions. Their efficient ... More
HONE: Higher-Order Network EmbeddingsJan 28 2018This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate ... More
Correlated Components Analysis --- Extracting Reliable Dimensions in Multivariate DataJan 26 2018How does one find data dimensions that are reliably expressed across repetitions? For example, in neuroscience one may want to identify combinations of brain signals that are reliably activated across multiple trials or subjects. For a clinical assessment ... More
Fast binary embeddings, and quantized compressed sensing with structured matricesJan 26 2018This paper deals with two related problems, namely distance-preserving binary embeddings and quantization for compressed sensing . First, we propose fast methods to replace points from a subset $\mathcal{X} \subset \mathbb{R}^n$, associated with the Euclidean ... More
Generative Adversarial Networks using Adaptive ConvolutionJan 25 2018Most existing GANs architectures that generate images use transposed convolution or resize-convolution as their upsampling algorithm from lower to higher resolution feature maps in the generator. We argue that this kind of fixed operation is problematic ... More
Deep Learning in Pharmacogenomics: From Gene Regulation to Patient StratificationJan 25 2018This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: (1) identification of novel regulatory variants located in noncoding domains and their function as applied to pharmacoepigenomics; (2) ... More
A Distributed Framework for the Construction of Transport MapsJan 25 2018The need to reason about uncertainty in large, complex, and multi-modal datasets has become increasingly common across modern scientific environments. The ability to transform samples from one distribution $P$ to another distribution $Q$ enables the solution ... More
MaskGAN: Better Text Generation via Filling in the ______Jan 23 2018Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several machine translation ... More
Expectation Learning for Adaptive Crossmodal Stimuli AssociationJan 23 2018The human brain is able to learn, generalize, and predict crossmodal stimuli. Learning by expectation fine-tunes crossmodal processing at different levels, thus enhancing our power of generalization and adaptation in highly dynamic environments. In this ... More
Generalized two-dimensional linear discriminant analysis with regularizationJan 23 2018Recent advances show that two-dimensional linear discriminant analysis (2DLDA) is a successful matrix based dimensionality reduction method. However, 2DLDA may encounter the singularity issue theoretically and the sensitivity to outliers. In this paper, ... More
Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral-Regularization AlgorithmsJan 22 2018We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes ... More
Offline A/B testing for Recommender SystemsJan 22 2018Before A/B testing online a new version of a recommender system, it is usual to perform some offline evaluations on historical data. We focus on evaluation methods that compute an estimator of the potential uplift in revenue that could generate this new ... More
Optimal Rates for Spectral-regularized Algorithms with Least-Squares Regression over Hilbert SpacesJan 20 2018In this paper, we study regression problems over a separable Hilbert space with the square loss, covering non-parametric regression over a reproducing kernel Hilbert space. We investigate a class of spectral-regularized algorithms, including ridge regression, ... More
A Deep Reinforcement Learning Chatbot (Short Version)Jan 20 2018We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both ... More
A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression dataJan 18 2018Gene expression data represents a unique challenge in predictive model building, because of the small number of samples $(n)$ compared to the huge amount of features $(p)$. This "$n<<p$" property has hampered application of deep learning techniques for ... More
Upgrading from Gaussian Processes to Student's-T ProcessesJan 18 2018Gaussian process priors are commonly used in aerospace design for performing Bayesian optimization. Nonetheless, Gaussian processes suffer two significant drawbacks: outliers are a priori assumed unlikely, and the posterior variance conditioned on observed ... More
On the Direction of Discrimination: An Information-Theoretic Analysis of Disparate Impact in Machine LearningJan 16 2018In the context of machine learning, disparate impact refers to a form of systematic discrimination whereby the output distribution of a model depends on the value of a sensitive attribute (e.g., race or gender). In this paper, we present an information-theoretic ... More
Time Series Segmentation through Automatic Feature LearningJan 16 2018Jan 26 2018Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge ... More
A3T: Adversarially Augmented Adversarial TrainingJan 12 2018Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. Most classification models, including ... More
Autoencoders and Probabilistic Inference with Missing Data: An Exact Solution for The Factor Analysis CaseJan 11 2018Latent variable models can be used to probabilistically "fill-in" missing data entries. The variational autoencoder architecture (Kingma and Welling, 2014; Rezende et al., 2014) includes a "recognition" or "encoder" network that infers the latent variables ... More
Improved asynchronous parallel optimization analysis for stochastic incremental methodsJan 11 2018Jan 12 2018As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. Unfortunately, conducting the theoretical analysis ... More
Sales forecasting and risk management under uncertainty in the media industryJan 09 2018In this work we propose a data-driven modelization approach for the management of advertising investments of a firm. First, we propose an application of dynamic linear models to the prediction of an economic variable, such as global sales, which can use ... More
Modeling sepsis progression using hidden Markov modelsJan 09 2018Characterizing a patient's progression through stages of sepsis is critical for enabling risk stratification and adaptive, personalized treatment. However, commonly used sepsis diagnostic criteria fail to account for significant underlying heterogeneity, ... More
PHOENICS: A universal deep Bayesian optimizerJan 04 2018In this work we introduce PHOENICS, a probabilistic global optimization algorithm combining ideas from Bayesian optimization with concepts from Bayesian kernel density estimation. We propose an inexpensive acquisition function balancing the explorative ... More
Gradient-based Optimization for Regression in the Functional Tensor-Train FormatJan 03 2018Jan 11 2018We consider the task of low-multilinear-rank functional regression, i.e., learning a low-rank parametric representation of functions from scattered real-valued data. Our first contribution is the development and analysis of an efficient gradient computation ... More
Deep Learning: A Critical AppraisalJan 02 2018Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) ... More
Proteomics Analysis of FLT3-ITD Mutation in Acute Myeloid Leukemia Using Deep Learning Neural NetworkDec 29 2017Deep 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 ... More
Finite-sample risk bounds for maximum likelihood estimation with arbitrary penaltiesDec 29 2017The MDL two-part coding $ \textit{index of resolvability} $ provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. However, the bound does not apply to unpenalized maximum likelihood estimation ... More
Kernel Robust Bias-Aware Prediction under Covariate ShiftDec 28 2017Under covariate shift, training (source) data and testing (target) data differ in input space distribution, but share the same conditional label distribution. This poses a challenging machine learning task. Robust Bias-Aware (RBA) prediction provides ... More
Robust Covariate Shift Prediction with General Losses and Feature ViewsDec 28 2017Covariate shift relaxes the widely-employed independent and identically distributed (IID) assumption by allowing different training and testing input distributions. Unfortunately, common methods for addressing covariate shift by trying to remove the bias ... More
The information bottleneck and geometric clusteringDec 27 2017The information bottleneck (IB) approach to clustering takes a joint distribution $P\!\left(X,Y\right)$ and maps the data $X$ to cluster labels $T$ which retain maximal information about $Y$ (Tishby et al., 1999). This objective results in an algorithm ... More
Merging $K$-means with hierarchical clustering for identifying general-shaped groupsDec 23 2017Clustering partitions a dataset such that observations placed together in a group are similar but different from those in other groups. Hierarchical and $K$-means clustering are two approaches but have different strengths and weaknesses. For instance, ... More
Mixtures of Matrix Variate Bilinear Factor AnalyzersDec 22 2017Over the years data is becoming increasingly higher dimensional, which has prompted an increased need for dimension reduction techniques, in particular for clustering and classification. Although dimension reduction in the area of clustering for multivariate ... More
Dropout Feature Ranking for Deep Learning ModelsDec 22 2017Deep neural networks are a promising technology achieving state-of-the-art results in biological and healthcare domains. Unfortunately, DNNs are notorious for their non-interpretability. Clinicians are averse to black boxes and thus interpretability is ... More
Adaptive Stochastic Dual Coordinate Ascent for Conditional Random FieldsDec 22 2017This work investigates training Conditional Random Fields (CRF) by Stochastic Dual Coordinate Ascent (SDCA). SDCA enjoys a linear convergence rate and a strong empirical performance for independent classification problems. However, it has never been used ... More
Combining Static and Dynamic Features for Multivariate Sequence ClassificationDec 20 2017Model precision in a classification task is highly dependent on the feature space that is used to train the model. Moreover, whether the features are sequential or static will dictate which classification method can be applied as most of the machine learning ... More
Query-Efficient Black-box Adversarial ExamplesDec 19 2017Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods --- substitute networks and coordinate-based ... More
Automatic Renal Segmentation in DCE-MRI using Convolutional Neural NetworksDec 19 2017Kidney function evaluation using dynamic contrast-enhanced MRI (DCE-MRI) images could help in diagnosis and treatment of kidney diseases of children. Automatic segmentation of renal parenchyma is an important step in this process. In this paper, we propose ... More
Towards the Augmented Pathologist: Challenges of Explainable-AI in Digital PathologyDec 18 2017Digital pathology is not only one of the most promising fields of diagnostic medicine, but at the same time a hot topic for fundamental research. Digital pathology is not just the transfer of histopathological slides into digital representations. The ... More
Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast AlgorithmsDec 17 2017We consider the problem of clustering with the longest leg path distance (LLPD) metric, which is informative for elongated and irregularly shaped clusters. We prove finite-sample guarantees on the performance of clustering with respect to this metric ... More
Sparse travel time tomography with adaptive dictionariesDec 16 2017Jan 14 2018We develop a 2D travel time tomography method which regularizes the inversion by modeling groups of slowness pixels from discrete slowness maps, called patches, as sparse linear combinations of atoms from a dictionary. We further propose to learn optimal ... More
WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning PotentialsDec 15 2017We introduce weighted atom-centered symmetry functions (wACSFs) as descriptors of a chemical system's geometry for use in the prediction of chemical properties such as enthalpies or potential energies via machine learning. The wACSFs are based on conventional ... More
Temporal Stability in Predictive Process MonitoringDec 12 2017Predictive business process monitoring is concerned with the analysis of events produced during the execution of a business process in order to predict as early as possible the final outcome of an ongoing case. Traditionally, predictive process monitoring ... More
Optimizing Human LearningDec 05 2017Spaced repetition is a technique for efficient memorization which uses repeated, spaced review of content to improve long-term retention. Can we find the optimal reviewing schedule to maximize the benefits of spaced repetition? In this paper, we introduce ... More
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local MinimaDec 03 2017We consider the problem of learning a one-hidden-layer neural network with non-overlapping convolutional layer and ReLU activation function, i.e., $f(\mathbf{Z}; \mathbf{w}, \mathbf{a}) = \sum_j a_j\sigma(\mathbf{w}^\top\mathbf{Z}_j)$, in which both the ... More
Rapid point-of-care Hemoglobin measurement through low-cost optics and Convolutional Neural Network based validationDec 01 2017A low-cost, robust, and simple mechanism to measure hemoglobin would play a critical role in the modern health infrastructure. Consistent sample acquisition has been a long-standing technical hurdle for photometer-based portable hemoglobin detectors which ... More
Towards Personalized Modeling of the Female Hormonal Cycle: Experiments with Mechanistic Models and Gaussian ProcessesNov 30 2017In this paper, we introduce a novel task for machine learning in healthcare, namely personalized modeling of the female hormonal cycle. The motivation for this work is to model the hormonal cycle and predict its phases in time, both for healthy individuals ... More
MR image reconstruction using deep density priorsNov 30 2017Jan 17 2018Purpose: MR image reconstruction exploits regularization to compensate for missing k-space data. In this work, we propose to learn the probability distribution of MR image patches with neural networks and use this distribution as prior information constraining ... More
Tighter Lifting-Free Convex Relaxations for Quadratic Matching ProblemsNov 29 2017In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original ... More
Leveraging the Crowd to Detect and Reduce the Spread of Fake News and MisinformationNov 27 2017Online social networking sites are experimenting with the following crowd-powered procedure to reduce the spread of fake news and misinformation: whenever a user is exposed to a story through her feed, she can flag the story as misinformation and, if ... More