Machine learning models that can exploit the inherent structure in data have gained prominence. In particular, there is a surge in deep learning solutions for graph-structured data, due to its wide-spread applicability in several fields. Graph attention networks (GAT), a recent addition to the broad class of feature learning models in graphs, utilizes the attention mechanism to efficiently learn continuous vector representations for semi-supervised learning problems. In this paper, we perform a detailed analysis of GAT models, and present interesting insights into their behavior. In particular, we show that the models are vulnerable to adversaries (rogue nodes) and hence propose novel regularization strategies to improve the robustness of GAT models. Using benchmark datasets, we demonstrate performance improvements on semi-supervised learning, using the proposed robust variant of GAT.

In 2002, the UCR time series classification archive was first released with sixteen datasets. It gradually expanded, until 2015 when it increased in size from 45 datasets to 85 datasets. In October 2018 more datasets were added, bringing the total to 128. The new archive contains a wide range of problems, including variable length series, but it still only contains univariate time series classification problems. One of the motivations for introducing the archive was to encourage researchers to perform a more rigorous evaluation of newly proposed time series classification (TSC) algorithms. It has worked: most recent research into TSC uses all 85 datasets to evaluate algorithmic advances. Research into multivariate time series classification, where more than one series are associated with each class label, is in a position where univariate TSC research was a decade ago. Algorithms are evaluated using very few datasets and claims of improvement are not based on statistical comparisons. We aim to address this problem by forming the first iteration of the MTSC archive, to be hosted at the website www.timeseriesclassification.com. Like the univariate archive, this formulation was a collaborative effort between researchers at the University of East Anglia (UEA) and the University of California, Riverside (UCR). The 2018 vintage consists of 30 datasets with a wide range of cases, dimensions and series lengths. For this first iteration of the archive we format all data to be of equal length, include no series with missing data and provide train/test splits.

When analysing graph structure, it can be difficult to determine whether patterns found are due to chance, or due to structural aspects of the process that generated the data. Hypothesis tests are often used to support such analyses. These allow us to make statistical inferences about which null models are responsible for the data, and they can be used as a heuristic in searching for meaningful patterns. The minimum description length (MDL) principle [6, 4] allows us to build such hypothesis tests, based on efficient descriptions of the data. Broadly: we translate the regularity we are interested in into a code for the data, and if this code describes the data more efficiently than a code corresponding to the null model, by a sufficient margin, we may reject the null model. This is a frequentist approach to MDL, based on hypothesis testing. Bayesian approaches to MDL for model selection rather than model rejection are more common, but for the purposes of pattern analysis, a hypothesis testing approach provides a more natural fit with existing literature. 1 We provide a brief illustration of this principle based on the running example of analysing the size of the largest clique in a graph. We illustrate how a code can be constructed to efficiently represent graphs with large cliques, and how the description length of the data under this code can be compared to the description length under a code corresponding to a null model to show that the null model is highly unlikely to have generated the data.

First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great practical success in deep learning, their behavior and performance on more general loss functions are not well understood. In this paper, we derive a non-autonomous system of differential equations, which is the continuous time limit of adaptive optimization methods. We prove global well-posedness of the system and we investigate the numerical time convergence of its forward Euler approximation. We study, furthermore, the convergence of its trajectories and give conditions under which the differential system, underlying all adaptive algorithms, is suitable for optimization. We discuss convergence to a critical point in the non-convex case and give conditions for the dynamics to avoid saddle points and local maxima. For convex and deterministic loss function, we introduce a suitable Lyapunov functional which allow us to study its rate of convergence. Several other properties of both the continuous and discrete systems are briefly discussed. The differential system studied in the paper is general enough to encompass many other classical algorithms (such as Heavy ball and Nesterov's accelerated method) and allow us to recover several known results for these algorithms.

Machine learning techniques have deeply rooted in our everyday life. However, since it is knowledge- and labor-intensive to pursuit good learning performance, human experts are heavily engaged in every aspect of machine learning. In order to make machine learning techniques easier to apply and reduce the demand for experienced human experts, automatic machine learning~(AutoML) has emerged as a hot topic of both in industry and academy. In this paper, we provide a survey on existing AutoML works. First, we introduce and define the AutoML problem, with inspiration from both realms of automation and machine learning. Then, we propose a general AutoML framework that not only covers almost all existing approaches but also guides the design for new methods. Afterward, we categorize and review the existing works from two aspects, i.e., the problem setup and the employed techniques. Finally, we provide a detailed analysis of AutoML approaches and explain the reasons underneath their successful applications. We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future researches.

An Upstate New York school is using facial recognition technology to help it spot possible school shooters or escaped felons on campus. Lockport City School District has installed a surveillance system in a high school, middle school and several elementary schools that scans students' faces to check for matches in its security database. The controversial move has attracted pushback from local parents, privacy advocates and some legislators who say it could invade students' privacy. Each client who chooses to install the system is able to choose which information is loaded into its database. They may source the material from local mugshot databases or images of students who've been expelled.

Watch our free Webinar with Q&A live on November 8th, 2018 at 2.30pm CET. Have you already heard about the IBM Machine Learning solution on Mainframe? If not, then this webinar is your chance to understand what it is all about. It introduces the key trends in Analytics and Data Management where machine learning represents one of the key elements. It explains Machine Learning concepts, the typical challenges encountered by Data Scientists and how many of those challenges can be addressed using the IBM machine Learning for z/OS.

Artificial intelligence is no longer a sci-fi movie trope--it's here and it's at the forefront of the fourth industrial revolution. Businesses are wising up, hiring smart and investing in artificial intelligence, a Salesforce director told Santa Rosa Junior College students and World Affairs Council of Sonoma County (WACSC) members Oct. 25. Jonathan Miranda is the director of strategy of Salesforce's technology division.That's just his job title, though. He is a futurist who studies where technology trends are headed. "Our team is aimed at the next two, three, five years" he said.

Medical students are losing the dexterity to stitch up their patients because they are spending too much time in front of screens. That's the claim from one professor of surgery who says trainee doctors are "less competent", compared to their older colleagues, at using their hands. Professor Roger Kneebone, from Imperial College London, says young people have so little experience of craft skills that they struggle with practical tasks. It's a worrying thought - but how true is it? Does screen time impact dexterity?

In the last few years, machine learning has been heavily promoted by sales and marketing teams as being the "holy grail" and as a set of technologies that will solve everyone's problems. After you've finished reading this post, you'll be able to cast a critical eye over any machine learning literature in the future and arrive at your own conclusions. Download our Machine Learning Industry Guide to identify specific ways in which machine learning software and platforms can benefit your business with industry insight. Machine learning is everywhere at the moment, so, let's bust some the myths that have been getting circulated in the past few years. Machines are going to take over the world!