Predicting the response of cancer cells to drugs is an important problem in pharmacogenomics. Recent efforts in generation of large scale datasets profiling gene expression and drug sensitivity in cell lines have provided a unique opportunity to study this problem. However, one major challenge is the small number of samples (cell lines) compared to the number of features (genes) even in these large datasets. We propose a collaborative filtering (CF) like algorithm for modeling gene-drug relationship to identify patients most likely to benefit from a treatment. Due to the correlation of gene expressions in different cell lines, the gene expression matrix is approximately low-rank, which suggests that drug responses could be estimated from a reduced dimension latent space of the gene expression. Towards this end, we propose a joint low-rank matrix factorization and latent linear regression approach. Experiments with data from the Genomics of Drug Sensitivity in Cancer database are included to show that the proposed method can predict drug-gene associations better than the state-of-the-art methods.

Fast Gradient Sign Method (FGSM) is a popular method to generate adversarial examples that make neural network models robust against perturbations. Despite its empirical success, its theoretical property is not well understood. This paper develops theory to explain the regularization effect of Generalized FGSM, a class of methods to generate adversarial examples. Motivated from the relationship between FGSM and LASSO penalty, the asymptotic properties of Generalized FGSM are derived in the Generalized Linear Model setting, which is essentially the 1-layer neural network setting with certain activation functions. In such simple neural network models, I prove that Generalized FGSM estimation is root n-consistent and weakly oracle under proper conditions. The asymptotic results are also highly similar to penalized likelihood estimation. Nevertheless, Generalized FGSM introduces additional bias when data sampling is not sign neutral, a concept I introduce to describe the balance-ness of the noise signs. Although the theory in this paper is developed under simple neural network settings, I argue that it may give insights and justification for FGSM in deep neural network settings as well.

Machine learning is part art and part science. When you look at machine learning algorithms, there is no one solution or one approach that fits all. There are several factors that can affect your decision to choose a machine learning algorithm. Some problems are very specific and require a unique approach. E.g. if you look at a recommender system, it's a very common type of machine learning algorithm and it solves a very specific kind of problem. While some other problems are very open and need a trial & error approach.

Complex networks are ubiquitous to several Computer Science domains. Centrality measures are an important analysis mechanism to uncover vital elements of complex networks. However, these metrics have high computational costs and requirements that hinder their applications in large real-world networks. In this tutorial, we explain how the use of neural network learning algorithms can render the application of the metrics in complex networks of arbitrary size. Moreover, the tutorial describes how to identify the best configuration for neural network training and learning such for tasks, besides presenting an easy way to generate and acquire training data. We do so by means of a general methodology, using complex network models adaptable to any application. We show that a regression model generated by the neural network successfully approximates the metric values and therefore are a robust, effective alternative in real-world applications. The methodology and proposed machine learning model use only a fraction of time with respect to other approximation algorithms, which is crucial in complex network applications.

Let's look at several techniques in machine learning and the math topics that are used in the process. In linear regression, we try to find the best fit line or hyperplane for a given set of data points. The parameters are found by minimizing the residual sum of squares. We find a critical point by setting the vector of derivatives of the residual sum of squares to the zero vector. By the second derivative test, if the Hessian of the residual sum of squares at a critical point is positive definite, then the residual sum of squares has a local minimum there.

Vertex centrality measures are a multi-purpose analysis tool, commonly used in many application environments to retrieve information and unveil knowledge from the graphs and network structural properties. However, the algorithms of such metrics are expensive in terms of computational resources when running real-time applications or massive real world networks. Thus, approximation techniques have been developed and used to compute the measures in such scenarios. In this paper, we demonstrate and analyze the use of neural network learning algorithms to tackle such task and compare their performance in terms of solution quality and computation time with other techniques from the literature. Our work offers several contributions. We highlight both the pros and cons of approximating centralities though neural learning. By empirical means and statistics, we then show that the regression model generated with a feedforward neural networks trained by the Levenberg-Marquardt algorithm is not only the best option considering computational resources, but also achieves the best solution quality for relevant applications and large-scale networks. Keywords: Vertex Centrality Measures, Neural Networks, Complex Network Models, Machine Learning, Regression Model

Tree-based ensemble methods, as Random Forests and Gradient Boosted Trees, have been successfully used for regression in many applications and research studies. Furthermore, these methods have been extended in order to deal with uncertainty in the output variable, using for example a quantile loss in Random Forests (Meinshausen, 2006). To the best of our knowledge, no extension has been provided yet for dealing with uncertainties in the input variables, even though such uncertainties are common in practical situations. We propose here such an extension by showing how standard regression trees optimizing a quadratic loss can be adapted and learned while taking into account the uncertainties in the input. By doing so, one no longer assumes that an observation lies into a single region of the regression tree, but rather that it belongs to each region with a certain probability. Experiments conducted on several data sets illustrate the good behavior of the proposed extension.

GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem [1-6]. We focus on the discriminator, which must perform classification under an (adversarially) shifting data distribution. When trained on sequential tasks, neural networks exhibit forgetting. For GANs, discriminator forgetting leads to training instability [1]. To counter forgetting, we encourage the discriminator to maintain useful representations by adding a self-supervision. Conditional GANs have a similar effect using labels. However, our self-supervised GAN does not require labels, and closes the performance gap between conditional and unconditional models. We show that, in doing so, the self-supervised discriminator learns better representations than regular GANs.

When big data is really small Machine Learning for all, what does it mean to democratize AI? A simple example Resources 5 7. 7 The last 40 years have witnessed massive adoption of the relational model It's hard to find any examples today of enterprises whose data isn't in a relational database Millions of human hours invested in building relational models and populating them with data Relational databases are rich with knowledge of the underlying domains that they model The availability and accuracy of large amounts of curated data has made it possible for humans (BI) and machines (AI) to learn from the past and to predict the future The relational model dominates data management 8. When big data is small 9. 9 What would a database do? Features Entities 2. Feature extraction query s: Aggregates (statistics) generated from model spec and feature extraction query 3. Model specification (e.g., "degree 2 ridge regression") 1. Database ID x 1 x 2 x 3 ... y 10. 1 0 Supported methods include Linear regression Polynomial regression Factorization machines Decision trees Linear SVM K-Means & K-Median clustering Principal component analysis Deep sum-product networks (with more on the way) Does it work for all model classes or methods?

Global demographic and economic changes have a critical impact on the total energy consumption, which is why demographic and economic parameters have to be taken into account when making predictions about the energy consumption. This research is based on the application of a multiple linear regression model and a neural network model, in particular multilayer perceptron, for predicting the energy consumption. Data from five Balkan countries has been considered in the analysis for the period 1995-2014. Gross domestic product, total number of population, and CO2 emission were taken as predictor variables, while the energy consumption was used as the dependent variable. The analyses showed that CO2 emissions have the highest impact on the energy consumption, followed by the gross domestic product, while the population number has the lowest impact. The results from both analyses are then used for making predictions on the same data, after which the obtained values were compared with the real values. It was observed that the multilayer perceptron model predicts better the energy consumption than the regression model.