Neural Information Processing Systems http://nips.cc/

Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired by various hypotheses about what makes multi-task settings difficult. The majority of these optimizers require per-task gradients, and introduce significant memory, runtime, and implementation overhead. We show that unitary scalarization, coupled with standard regularization and stabilization techniques from single-task learning, matches or improves upon the performance of complex multi-task optimizers in popular supervised and reinforcement learning settings. We then present an analysis suggesting that many specialized multi-task optimizers can be partly interpreted as forms of regularization, potentially explaining our surprising results. We believe our results call for a critical reevaluation of recent research in the area.

A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard methodology has a serious flaw - virtually all of the defenses are evaluated against non-adaptive attacks leading to overly optimistic robustness estimates. We perform a thorough robustness analysis of 7 of the most popular defenses spanning the entire spectrum of strategies, i.e., aimed at improving the graph, the architecture, or the training. The results are sobering - most defenses show no or only marginal improvement compared to an undefended baseline. We advocate using custom adaptive attacks as a gold standard and we outline the lessons we learned from successfully designing such attacks. Moreover, our diverse collection of perturbed graphs forms a (black-box) unit test offering a first glance at a model's robustness.

Jan Lipavský became the Minister of Foreign Affairs of the Czech Republic on December 17, 2021. Prior to becoming minister, Jan Lipavsky entered government as a parliamentary representative. He served four years in the Chamber of Deputies as the Vice-Chairman on the Committee on Foreign Affairs and Committee on Defense. Likewise, he was on three other committees: the Standing Committee on Hybrid Threats, the Subcommittee on Migration and Asylum Policy, and the Subcommittee on Defense, Cyber, and Security Policy and Strategic Concepts of the Czech Republic. Lipavský specializes primarily in energy and international security and hybrid threats.

Will AI take over the world? Or, more to the point, will it take over the humankind? It seems to have invaded the public consciousness, sparking concerns that AI will take away jobs. This fear is driven in part by companies using AI to deliver cost savings across their businesses, including areas related to labor. But AI is much more than that.

Will AI take over the world? Or, more to the point, will it take over the humankind? It seems to have invaded the public consciousness, sparking concerns that AI will take away jobs. This fear is driven in part by companies using AI to deliver cost savings across their businesses, including areas related to labor. But AI is much more than that.

The U.S. military got is first big taste of artificial intelligence with Project Maven. An Air Force initiative, it began more than a year ago as an experiment using machine learning algorithms developed by Google to analyze full-motion video surveillance. The project has received high praise within military circles for giving operators in the field instant access to the type of intelligence that typically would have taken a long time for geospatial data analysts to produce. Project Maven has whetted the military's appetite for artificial intelligence tools. And this is creating pressure on the National Geospatial-Intelligence Agency to jump on the AI bandwagon and start delivering Maven-like products and services.

Deep neural networks (DNNs) have enabled great progress in a variety of application areas, including image processing, text analysis, and speech recognition. DNNs are also being incorporated as an important component in many cyber-physical systems. For instance, the vision system of a self-driving car can take advantage of DNNs to better recognize pedestrians, vehicles, and road signs. However, recent research has shown that DNNs are vulnerable to adversarial examples: Adding carefully crafted adversarial perturbations to the inputs can mislead the target DNN into mislabeling them during run time. Such adversarial examples raise security and safety concerns when applying DNNs in the real world.

The innovative reapplication of a multiagent system for human-in-the-loop (HIL) simulation was a consequence of appropriate agent-oriented design. The use of intelligent agents for simulating human decision making offers the potential for analysis and design methodologies that do not distinguish between agent and human until implementation. With this as a driver in the design process, the construction of systems in which humans and agents can be interchanged is simplified. Two systems have been constructed and deployed to provide defense analysts with the tools required to advise and assist the Australian Defense Force in the conduct of maritime surveillance and patrol. The experiences gained from this process indicate that it is simpler, both in design and implementation, to add humans to a system designed for intelligent agents than it is to add intelligent agents to a system designed for humans.

The Robot World-Cup Soccer (RoboCup) is an attempt to foster AI and intelligent robotics research by providing a standard problem where a wide range of technologies can be integrated and examined. The first RoboCup competition will be held at the Fifteenth International Joint Conference on Artificial Intelligence in Nagoya, Japan. A robot team must actually perform a soccer game, incorporating various technologies, including design principles of autonomous agents, multiagent collaboration, strategy acquisition, real-time reasoning, robotics, and sensor fusion. RoboCup is a task for a team of multiple fast-moving robots under a dynamic environment. Although RoboCup's final target is a world cup with real robots, RoboCup offers a software platform for research on the software aspects of RoboCup.