Machine learning models repeatedly outperform interpretable, parametric models like the linear regression model. The gains in performance have a price: The models operate as black boxes which are not interpretable. Fortunately, there are many methods that can make machine learning models interpretable. Feature importance: Which were the most important features? Feature effects: How does a feature influence the prediction?

Mosquitoes are vectors of many human diseases. In particular, Aedes \ae gypti (Linnaeus) is the main vector for Chikungunya, Dengue, and Zika viruses in Latin America and it represents a global threat. Public health policies that aim at combating this vector require dependable and timely information, which is usually expensive to obtain with field campaigns. For this reason, several efforts have been done to use remote sensing due to its reduced cost. The present work includes the temporal modeling of the oviposition activity (measured weekly on 50 ovitraps in a north Argentinean city) of Aedes \ae gypti (Linnaeus), based on time series of data extracted from operational earth observation satellite images. We use are NDVI, NDWI, LST night, LST day and TRMM-GPM rain from 2012 to 2016 as predictive variables. In contrast to previous works which use linear models, we employ Machine Learning techniques using completely accessible open source toolkits. These models have the advantages of being non-parametric and capable of describing nonlinear relationships between variables. Specifically, in addition to two linear approaches, we assess a Support Vector Machine, an Artificial Neural Networks, a K-nearest neighbors and a Decision Tree Regressor. Considerations are made on parameter tuning and the validation and training approach. The results are compared to linear models used in previous works with similar data sets for generating temporal predictive models. These new tools perform better than linear approaches, in particular Nearest Neighbor Regression (KNNR) performs the best. These results provide better alternatives to be implemented operatively on the Argentine geospatial Risk system that is running since 2012.

Electroencephalogram, an influential equipment for analyzing humans activities and recognition of seizure attacks can play a crucial role in designing accurate systems which can distinguish ictal seizures from regular brain alertness, since it is the first step towards accomplishing a high accuracy computer aided diagnosis system (CAD). In this article a novel approach for classification of ictal signals with wavelet based cross frequency coupling (CFC) is suggested. After extracting features by wavelet based CFC, optimal features have been selected by t-test and quadratic discriminant analysis (QDA) have completed the Classification.

We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is often possible to accurately estimate this "learnability" even when given an amount of data that is too small to reliably learn any accurate model. Our first result applies to the setting where the data is drawn from a $d$-dimensional distribution with isotropic covariance, and the label of each datapoint is an arbitrary noisy function of the datapoint. In this setting, we show that with $O(\sqrt{d})$ samples, one can accurately estimate the fraction of the variance of the label that can be explained via the best linear function of the data. We extend these techniques to the setting of binary classification, where we show that in an analogous setting, the prediction error of the best linear classifier can be accurately estimated given $O(\sqrt{d})$ labeled samples. Note that in both the linear regression and binary classification settings, even if there is no noise in the labels, a sample size linear in the dimension, $d$, is required to \emph{learn} any function correlated with the underlying model. We further extend our estimation approach to the setting where the data distribution has an (unknown) arbitrary covariance matrix, allowing these techniques to be applied to settings where the model class consists of a linear function applied to a nonlinear embedding of the data. Finally, we demonstrate the practical viability of these approaches on synthetic and real data. This ability to estimate the explanatory value of a set of features (or dataset), even in the regime in which there is too little data to realize that explanatory value, may be relevant to the scientific and industrial settings for which data collection is expensive and there are many potentially relevant feature sets that could be collected.

In regression modelling approach, the main step is to fit the regression line as close as possible to the target variable. In this process most algorithms try to fit all of the data in a single line and hence fitting all parts of target variable in one go. It was observed that the error between predicted and target variable usually have a varying behavior across the various quantiles of the dependent variable and hence single point diagnostic like MAPE has its limitation to signify the level of fitness across the distribution of Y(dependent variable). To address this problem, a novel approach is proposed in the paper to deal with regression fitting over various quantiles of target variable. Using this approach we have significantly improved the eccentric behavior of the distance (error) between predicted and actual value of regression. Our proposed solution is based on understanding the segmented behavior of the data with respect to the internal segments within the data and approach for retrospectively fitting the data based on each quantile behavior. We believe exploring and using this approach would help in achieving better and more explainable results in most settings of real world data modelling problems.

We review several recently proposed post-selection inference frameworks and assess their transferability to the component-wise functional gradient descent algorithm (CFGD) under normality assumption for model errors, also known as $L_2$-Boosting. The CFGD is one of the most versatile toolboxes to analyze data, as it scales well to high-dimensional data sets, allows for a very flexible definition of additive regression models and incorporates inbuilt variable selection. %After addressing several issues associated with Due to the iterative nature, which can repeatedly select the same component to update, an inference framework for component-wise boosting algorithms requires adaptations of existing approaches; we propose tests and confidence intervals for linear, grouped and penalized additive model components estimated using the $L_2$-boosting selection process. We apply our framework to the prostate cancer data set and investigate the properties of our concepts in simulation studies. %The most general and promising selective inference framework for $L_2$-Boosting as well as for more general gradient-descent boosting algorithms is an sampling approach which constitutes an adoption of the recently proposed method by Yang et al. (2016).

In this article we present a method by which we can reduce a time series into a single point in $\mathbb{R}^{13}$. We have chosen 13 dimensions so as to prevent too many points from being labeled as "noise." When using a Euclidean (or Mahalanobis) metric, a simple clustering algorithm will with near certainty label the majority of points as "noise." On pure physical considerations, this is not possible. Included in our 13 dimensions are four parameters which describe the coefficients of a cubic polynomial attached to a Gaussian picking up a general trend, four parameters picking up periodicity in a time series, two each for amplitude of a wave and period of a wave, and the final five report the "leftover" noise of the detrended and aperiodic time series. Of the final five parameters, four are the centralized probabilistic moments, and the final for the relative size of the series. The first main contribution of this work is to apply a theorem of quantum mechanics about the completeness of the solutions to the quantum harmonic oscillator on $L^2(\mathbb{R})$ to estimating trends in time series. The second main contribution is the method of fitting parameters. After many numerical trials, we realized that methods such a Newton-Rhaphson and Levenberg-Marquardt converge extremely fast if the initial guess is good. Thus we guessed many initial points in our parameter space and computed only a few iterations, a technique common in Keogh's work on time series clustering. Finally, we have produced a model which gives incredibly accurate results quickly. We ackowledge that there are faster methods as well of more accurate methods, but this work shows that we can still increase computation speed with little, if any, cost to accuracy in the sense of data clustering.

We study the problem of sampling from a distribution where the negative logarithm of the target density is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially non-convex inside this ball. We study both overdamped and underdamped Langevin MCMC and prove upper bounds on the time required to obtain a sample from a distribution that is within $\epsilon$ of the target distribution in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{d}{\epsilon^2}\right)$, where $d$ is the dimension of the underlying space. For the second-order method (underdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{\sqrt{d}}{\epsilon}\right)$ for some explicit positive constant $c$. Surprisingly, the convergence rate is only polynomial in the dimension $d$ and the target accuracy $\epsilon$. It is however exponential in the problem parameter $LR^2$, which is a measure of non-logconcavity of the target distribution.

Gradient descent relies on trial and error to optimize an algorithm, aiming for minima in a 3D landscape. Ali Rahimi, a researcher in artificial intelligence (AI) at Google in San Francisco, California, took a swipe at his field last December--and received a 40-second ovation for it. Speaking at an AI conference, Rahimi charged that machine learning algorithms, in which computers learn through trial and error, have become a form of "alchemy." Researchers, he said, do not know why some algorithms work and others don't, nor do they have rigorous criteria for choosing one AI architecture over another. Now, in a paper presented on 30 April at the International Conference on Learning Representations in Vancouver, Canada, Rahimi and his collaborators document examples of what they see as the alchemy problem and offer prescriptions for bolstering AI's rigor.

There are lots of differences between traditional statistical modeling and machine learning. Machine learning depends on computer algorithms, few estimates, and small to large datasets to produce predictions of high accuracy. Statistical modeling, on the other hand, depends on human talents, mathematical equations, and many assumptions to predict the "best estimate." The amount of training data needed to build a comprehensive machine learning model is highly debated. The type of data determines the number of features.