The real-time crash likelihood prediction has been an important research topic. Various classifiers, such as support vector machine (SVM) and tree-based boosting algorithms, have been proposed in traffic safety studies. However, few research focuses on the missing data imputation in real-time crash likelihood prediction, although missing values are commonly observed due to breakdown of sensors or external interference. Besides, classifying imbalanced data is also a difficult problem in real-time crash likelihood prediction, since it is hard to distinguish crash-prone cases from non-crash cases which compose the majority of the observed samples. In this paper, principal component analysis (PCA) based approaches, including LS-PCA, PPCA, and VBPCA, are employed for imputing missing values, while two kinds of solutions are developed to solve the problem in imbalanced data. The results show that PPCA and VBPCA not only outperform LS-PCA and other imputation methods (including mean imputation and k-means clustering imputation), in terms of the root mean square error (RMSE), but also help the classifiers achieve better predictive performance. The two solutions, i.e., cost-sensitive learning and synthetic minority oversampling technique (SMOTE), help improve the sensitivity by adjusting the classifiers to Corresponding author Email address: chenxiqun@zju.edu.cn Keywords: Real-time crash likelihood prediction, PCA-based missing data imputation, cost-sensitive learning, SMOTE, support vector machine, AdaBoost 1. Introduction Prediction of traffic crash has been a major research topic in transportation safety studies. Crashes, especially on urban expressways, can trigger heavy traffic congestions, impose huge external costs, and reduce the level of service of transportation infrastructures. Therefore, the accurate and reliable prediction of crash risks is critical to the success of proactive safety management strategies on urban expressways. There have been fruitful studies in the domain of the real-time crash likelihood estimation (Abdel-Aty and Pemmanaboina, 2006; Abdel-Aty et al., 2007, 2008; Ahmed and Abdel-Aty, 2012). It has been reported that crash occurrence was affected by four major factors: real-time traffic state, drivers' behavior, environment factors, and road geometry (Ahmed and Abdel-Aty, 2013b).

The fundamental task of general density estimation $p(x)$ has been of keen interest to machine learning. In this work, we attempt to systematically characterize methods for density estimation. Broadly speaking, most of the existing methods can be categorized into either using: \textit{a}) autoregressive models to estimate the conditional factors of the chain rule, $p(x_{i}\, |\, x_{i-1}, \ldots)$; or \textit{b}) non-linear transformations of variables of a simple base distribution. Based on the study of the characteristics of these categories, we propose multiple novel methods for each category. For example we proposed RNN based transformations to model non-Markovian dependencies. Further, through a comprehensive study over both real world and synthetic data, we show for that jointly leveraging transformations of variables and autoregressive conditional models, results in a considerable improvement in performance. We illustrate the use of our models in outlier detection and image modeling. Finally we introduce a novel data driven framework for learning a family of distributions.

Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provide a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution. The TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution as defined in graph signal processing. Since no approximation to the convolution is needed, TAGCN exhibits better performance than existing spectral CNNs on a number of data sets and is also computationally simpler than other recent methods.

Active learning aims to train a classifier as fast as possible with as few labels as possible. The core element in virtually any active learning strategy is the criterion that measures the usefulness of the unlabeled data based on which new points to be labeled are picked. We propose a novel approach which we refer to as maximizing variance for active learning or MVAL for short. MVAL measures the value of unlabeled instances by evaluating the rate of change of output variables caused by changes in the next sample to be queried and its potential labelling. In a sense, this criterion measures how unstable the classifier's output is for the unlabeled data points under perturbations of the training data. MVAL maintains, what we refer to as, retraining information matrices to keep track of these output scores and exploits two kinds of variance to measure the informativeness and representativeness, respectively. By fusing these variances, MVAL is able to select the instances which are both informative and representative. We employ our technique both in combination with logistic regression and support vector machines and demonstrate that MVAL achieves state-of-the-art performance in experiments on a large number of standard benchmark datasets.

Imagine this scenario: In a clinical trial investigating the toxicity of a new chemotherapy drug to treat breast cancer, some patients drop out of the trial before completion for various reasons, hence we do not have the data for final outcome on the dropped out patients. What if the patients who drop out of the trial before completion are the ones who experienced toxicity and are unwilling to continue the treatment, this reason however is not recorded in the database and the patients are marked as "lost to followup". If the investigators were to analyze the data using conventional methods where loss to followup is ignored and not properly accounted for, they will estimate the toxicity to be far less than what it really is. These results can lead to adapting a drug, that is otherwise unsafe. Similarly if patients who are feeling better dropout of the trial before completion, the estimates of toxicity would be far greater than the real value, leading to rejection of a potential lifesaver drug.

Chemotherapeutic response of cancer cells to a given compound is one of the most fundamental information one requires to design anti-cancer drugs. Recent advances in producing large drug screens against cancer cell lines provided an opportunity to apply machine learning methods for this purpose. In addition to cytotoxicity databases, considerable amount of drug-induced gene expression data has also become publicly available. Following this, several methods that exploit omics data were proposed to predict drug activity on cancer cells. However, due to the complexity of cancer drug mechanisms, none of the existing methods are perfect. One possible direction, therefore, is to combine the strengths of both the methods and the databases for improved performance. We demonstrate that integrating a large number of predictions by the proposed method improves the performance for this task. The predictors in the ensemble differ in several aspects such as the method itself, the number of tasks method considers (multi-task vs. single-task) and the subset of data considered (sub-sampling). We show that all these different aspects contribute to the success of the final ensemble. In addition, we attempt to use the drug screen data together with two novel signatures produced from the drug-induced gene expression profiles of cancer cell lines. Finally, we evaluate the method predictions by in vitro experiments in addition to the tests on data sets.The predictions of the methods, the signatures and the software are available from http://mtan.etu.edu.tr/drug-response-prediction/.

The combination of high-dimensionality and disparity of time scales encountered in many problems in computational physics has motivated the development of coarse-grained (CG) models. In this paper, we advocate the paradigm of data-driven discovery for extract- ing governing equations by employing fine-scale simulation data. In particular, we cast the coarse-graining process under a probabilistic state-space model where the transition law dic- tates the evolution of the CG state variables and the emission law the coarse-to-fine map. The directed probabilistic graphical model implied, suggests that given values for the fine- grained (FG) variables, probabilistic inference tools must be employed to identify the cor- responding values for the CG states and to that end, we employ Stochastic Variational In- ference. We advocate a sparse Bayesian learning perspective which avoids overfitting and reveals the most salient features in the CG evolution law. The formulation adopted enables the quantification of a crucial, and often neglected, component in the CG process, i.e. the pre- dictive uncertainty due to information loss. Furthermore, it is capable of reconstructing the evolution of the full, fine-scale system. We demonstrate the efficacy of the proposed frame- work in high-dimensional systems of random walkers.

In the past decade, terms like machine learning, artificial intelligence, and data mining are becoming greater buzzwords as computing power, APIs, and the massively increased availability of data enable new technologies like self-driving cars. However, we've been using methodologies like machine learning in psychometrics for decades. So much of the hype is just hype. Unfortunately, there is no widely agreed-upon definition, and as Wikipedia notes, machine learning is often conflated with data mining. A broad definition from Wikipedia is that machine learning explores the study and construction of algorithms that can learn from and make predictions on data.

So what were the answers popping in your head? Now some of you might laugh and say how on earth can you predict so far ahead, predicting things 100 yrs into future is crazy. What makes you say Regression Will continue to be used in 2118? Well the answer is Lindy effect. Yes, the heuristic I am using to predict this is Lindy Effect.

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex time series data. Fully probabilistic SSMs, however, are often found hard to train, even for smaller problems. To overcome this limitation, we propose a novel model formulation and a scalable training algorithm based on doubly stochastic variational inference and Gaussian processes. In contrast to existing work, the proposed variational approximation allows one to fully capture the latent state temporal correlations. These correlations are the key to robust training. The effectiveness of the proposed PR-SSM is evaluated on a set of real-world benchmark datasets in comparison to state-of-the-art probabilistic model learning methods. Scalability and robustness are demonstrated on a high dimensional problem.