We are concerned with the vulnerability of computer vision models to distributional shifts. We cast this problem in terms of combinatorial optimization, evaluating the regions in the input space where a (black-box) model is more vulnerable. This is carried out by combining image transformations from a given set and standard search algorithms. We embed this idea in a training procedure, where we define new data augmentation rules over iterations, accordingly to the image transformations that the current model is most vulnerable to. An empirical evaluation on classification and semantic segmentation problems suggests that the devised algorithm allows to train models more robust against content-preserving image transformations, and in general, against distributional shifts.

Graph kernels have become an established and widely-used technique for solving classification tasks on graphs. This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years. We describe and categorize graph kernels based on properties inherent to their design, such as the nature of their extracted graph features, their method of computation and their applicability to problems in practice. In an extensive experimental evaluation, we study the classification accuracy of a large suite of graph kernels on established benchmarks as well as new datasets. We compare the performance of popular kernels with several baseline methods and study the effect of applying a Gaussian RBF kernel to the metric induced by a graph kernel. In doing so, we find that simple baselines become competitive after this transformation on some datasets. Moreover, we study the extent to which existing graph kernels agree in their predictions (and prediction errors) and obtain a data-driven categorization of kernels as result. Finally, based on our experimental results, we derive a practitioner's guide to kernel-based graph classification.

In many research fields, the sizes of the existing datasets vary widely. Hence, there is a need for machine learning techniques which are well-suited for these different datasets. One possible technique is the self-organizing map (SOM), a type of artificial neural network which is, so far, weakly represented in the field of machine learning. The SOM's unique characteristic is the neighborhood relationship of the output neurons. This relationship improves the ability of generalization on small datasets. SOMs are mostly applied in unsupervised learning and few studies focus on using SOMs as supervised learning approach. Furthermore, no appropriate SOM package is available with respect to machine learning standards and in the widely used programming language Python. In this paper, we introduce the freely available SUpervised Self-organIzing maps (SUSI) Python package which performs supervised regression and classification. The implementation of SUSI is described with respect to the underlying mathematics. Then, we present first evaluations of the SOM for regression and classification datasets from two different domains of geospatial image analysis. Despite the early stage of its development, the SUSI framework performs well and is characterized by only small performance differences between the training and the test datasets. A comparison of the SUSI framework with existing Python and R packages demonstrates the importance of the SUSI framework. In future work, the SUSI framework will be extended, optimized and upgraded e.g. with tools to better understand and visualize the input data as well as the handling of missing and incomplete data.

Mobile robots, performing long-term manipulation activities in human environments, have to perceive a wide variety of objects possessing very different visual characteristics and need to reliably keep track of these throughout the execution of a task. In order to be efficient, robot perception capabilities need to go beyond what is currently perceivable and should be able to answer queries about both current and past scenes. In this paper we investigate a perception system for long-term robot manipulation that keeps track of the changing environment and builds a representation of the perceived world. Specifically we introduce an amortized component that spreads perception tasks throughout the execution cycle. The resulting query driven perception system asynchronously integrates results from logged images into a symbolic and numeric (what we call sub-symbolic) representation that forms the perceptual belief state of the robot.

A growing interest in tasks involving language understanding by the NLP community has led to the need for effective semantic parsing and inference. Modern NLP systems use semantic representations that do not quite fulfill the nuanced needs for language understanding: adequately modeling language semantics, enabling general inferences, and being accurately recoverable. This document describes underspecified logical forms (ULF) for Episodic Logic (EL), which is an initial form for a semantic representation that balances these needs. ULFs fully resolve the semantic type structure while leaving issues such as quantifier scope, word sense, and anaphora unresolved; they provide a starting point for further resolution into EL, and enable certain structural inferences without further resolution. This document also presents preliminary results of creating a hand-annotated corpus of ULFs for the purpose of training a precise ULF parser, showing a three-person pairwise interannotator agreement of 0.88 on confident annotations. We hypothesize that a divide-and-conquer approach to semantic parsing starting with derivation of ULFs will lead to semantic analyses that do justice to subtle aspects of linguistic meaning, and will enable construction of more accurate semantic parsers.

The intelligent Processing technique is more and more attractive to researchers due to its ability to deal with key problems in Vehicular Ad hoc networks. However, several problems in applying intelligent processing technologies in VANETs remain open. The existing applications are comprehensively reviewed and discussed, and classified into different categories in this paper. Their strategies, advantages/disadvantages, and performances are elaborated. By generalizing different tactics in various applications related to different scenarios of VANETs and evaluating their performances, several promising directions for future research have been suggested.

Elizabeth Keatinge tells us about Elon Musk's DNA Friend makes fun of the at-home DNA testing craze. The government's contempt of court case against Tesla CEO Elon Musk is moving forward. Federal Judge Alison Nathan has set a court date of April 4 to hold oral arguments. The Securities and Exchange Commission is asking Nathan to find Musk in contempt for allegedly violating terms of an October court-approved securities fraud settlement with a Feb. 19 tweet. In the tweet, Musk wrote: "Tesla made 0 cars in 2011, but will make around 500k in 2019."

The team at Guardian Voice Labs is experimenting with generating an audio news summary by blending human and synthetic voices. It's designed for Google Assistant and based on existing Guardian journalism and curation. The idea is to capitalise on the text-to-speech technology on the Assistant platform, and create a new way for people to digest the news of the day. To better explain exactly how the technology works, Jordan Erica Webber invited the product manager for the Guardian Voice Lab, Jeremy Pennycook, into the studio.

Last December, entrepreneur Amin Khoury gave Northeastern University's College of Computer Science a $50 million gift. The money was slated for programs that would help new graduates compete in a marketplace increasingly dominated by artificial intelligence and automation. The university's press release touted, "As the global economy adapts to the influence of artificial intelligence … Northeastern is empowering humans to be agile learners, thinkers, and creators, beyond the capacity of any machine." The school, like quite a few others, is reimagining itself as an incubator for skills that are difficult to automate: creativity, imagination, mental flexibility. Indeed, Joseph Aoun, Northeastern's president, literally wrote the book on this.

McDonald's is looking to supercharge sales by using A.I. backed software capable of tailoring products to customers in real-time. America's most iconic fast food chain announced that it has acquired an Israeli company, Dynamic Yield, whose software will use machine-learning to adapt digital menus to feature products based on time, location, preference, demand and more. The Wall Street Journal reported that McDonald's deal to purchase Dynamic Yield was closed at $300 million but neither company has confirmed. McDonald's has revamped its image across the world by deploying a mobile app, renovating stores, and now buying a tech company to help personalize menu items. McDonald's purchase Israeli company, Dynamic Yield which employs data and analytics to increase sales.