LIVERMORE, CALIFORNIA – Today, U.S. Secretary of Energy Rick Perry and Founder of the Weill Family Foundation, Mr. Sandy Weill, signed a Memorandum of Understanding to formally initiate a public-private partnership for artificial intelligence (AI), neurological disorders, and related subjects. The partnership will apply DOE-fueled AI capabilities to advance transformative scientific opportunities in biomedical and public health research. The MOU will foster collaboration to demonstrate AI based research breakthroughs that span from basic science focused on a better understanding of how the brain functions, to clinical and translational research focused on developing novels methods for preventing, treating, and repairing damage caused by diseases and disorders of the brain. "Artificial Intelligence has the power to literally change the world we live in by tackling some of the biggest problems facing humanity – from improving our environment, to advancing our understanding of the cosmos; from increasing cyber security to improving crop production," said U.S. Secretary of Energy Rick Perry. "This Memorandum of Understanding between the Department of Energy and Weill Family Foundation will advance groundbreaking AI research and development in health sciences that will enhance our overall security and improve our quality of life."

RIYADH: The royal decree to establish an artificial intelligence (AI) center will enhance the drive toward innovation and digital transformation in Saudi Arabia, according to Minister of Communications and Information Technology Abdullah Al-Sawaha. King Salman issued the decree on Friday, to establish the National Center for Artificial Intelligence and an organization called the National Data Management Office, which will be linked to the Saudi Data and Artificial Intelligence Authority. The establishment of the center came in line with the objectives of the Kingdom's Vision 2030 program, and will help develop performance efficiency through the applications of AI and big data, Al-Sawaha said. He added that the establishment of the center was a clear indication of the Kingdom's determination to develop its digital capabilities and build a future based on AI and innovation. Al-Sawaha said that AI would enhance productivity, boost decision-making processes across all sectors, render services provided to Saudi citizens more innovative, and open new horizons to stimulate entrepreneurship and support young people.

In recent years the power systems research community has seen an explosion of work applying operations research techniques to challenging power network optimization problems. Regardless of the application under consideration, all of these works rely on power system test cases for evaluation and validation. However, many of the well established power system test cases were developed as far back as the 1960s with the aim of testing AC power flow algorithms. It is unclear if these power flow test cases are suitable for power system optimization studies. This report surveys all of the publicly available AC transmission system test cases, to the best of our knowledge, and assess their suitability for optimization tasks. It finds that many of the traditional test cases are missing key network operation constraints, such as line thermal limits and generator capability curves. To incorporate these missing constraints, data driven models are developed from a variety of publicly available data sources. The resulting extended test cases form a compressive archive, NESTA, for the evaluation and validation of power system optimization algorithms.

The article presents a solution approach for the Torpedo Scheduling Problem, an operational planning problem found in steel production. The problem consists of the integrated scheduling and routing of torpedo cars, i. e. steel transporting vehicles, from a blast furnace to steel converters. In the continuous metallurgic transformation of iron into steel, the discrete transportation step of molten iron must be planned with considerable care in order to ensure a continuous material flow. The problem is solved by a Simulated Annealing algorithm, coupled with an approach of reducing the set of feasible material assignments. The latter is based on logical reductions and lower bound calculations on the number of torpedo cars. Experimental investigations are performed on a larger number of problem instances, which stem from the 2016 implementation challenge of the Association of Constraint Programming (ACP). Our approach was ranked first (joint first place) in the 2016 ACP challenge and found optimal solutions for all used instances in this challenge.

Bias is known to be an impediment to fair decisions in many domains such as human resources, the public sector, health care etc. Recently, hope has been expressed that the use of machine learning methods for taking such decisions would diminish or even resolve the problem. At the same time, machine learning experts warn that machine learning models can be biased as well. In this article, our goal is to explain the issue of bias in machine learning from a technical perspective and to illustrate the impact that biased data can have on a machine learning model. To reach such a goal, we develop interactive plots to visualizing the bias learned from synthetic data.

Deep networks are well-known to be fragile to adversarial attacks. Using several standard image datasets and established attack mechanisms, we conduct an empirical analysis of deep representations under attack, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning in order to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also can detect previously unseen adversarial samples. Quantitative experiments show improvement of robustness accuracy by up to 4\% and detection efficiency by up to 6\% according to Area Under Curve (AUC) score over baselines.

In this paper, we address the challenging problem of learning from imbalanced data using a Nearest-Neighbor (NN) algorithm. In this setting, the minority examples typically belong to the class of interest requiring the optimization of specific criteria, like the F-Measure. Based on simple geometrical ideas, we introduce an algorithm that reweights the distance between a query sample and any positive training example. This leads to a modification of the Voronoi regions and thus of the decision boundaries of the NN algorithm. We provide a theoretical justification about the weighting scheme needed to reduce the False Negative rate while controlling the number of False Positives. We perform an extensive experimental study on many public imbalanced datasets, but also on large scale non public data from the French Ministry of Economy and Finance on a tax fraud detection task, showing that our method is very effective and, interestingly, yields the best performance when combined with state of the art sampling methods.

The task can be modeled as building a graph for a given text, whose nodes represent events and edges are labeled with temporal relations correspondingly. Figure 1a illustrates such a graph for the text shown therein. The nodes assassination, slaughtered, rampage, war, and Hutu are the candidate events, and different types of edges specify different temporal relations between them: assassination is BEFORE rampage, rampage INCLUDES slaughtered, and the relation between slaughtered and war is VAGUE. Since "Hutu" is actually not an event, a system is expected to annotate the relations between "Hutu" and all other nodes in the graph as NONE (i.e., no relation). As far as we know, all existing systems treat this task as a pipeline of two separate subtasks, (a) Temporal Relation Graph (b) Pipeline Model (c) Structured Joint Model Figure 1: An illustration of event and relation models in our proposed joint framework.

The 1991 sci-fi film Terminator 2 predicted that artificial intelligence (AI) software known as Skynet would become self-aware on August 29, 1997, and rapidly take over the world. Today, even as we celebrate avoiding such an extreme outcome for 22 years and counting, we're continually scanning the field for new developments in the world of AI. Read on, and listen to our podcast with GAO's Chief Scientist and Managing Director, Tim Persons, to learn more about our work in this area. AI is far from developing into anything like Skynet. That would require AI technologies with broad reasoning abilities, sometimes called third-wave AI, which are highly unlikely in the foreseeable future.

The concepts of hybrid threat and hybrid warfare are, presently, key concepts within strategic studies1 and intelligence studies2, with a core relevance in the new defense and security context that was enabled by the twenty-first century's Fourth Industrial Revolution, driven by the synergization of cyberspace and artificial intelligence (AI), fueled by the accelerated and disruptive exponential expansion of machine learning (ML) [1, 2, 3]. Cyber operations, presently, constitute a key determinant component of hybrid strategies and tactics that configure the profile of hybrid threats and hybrid warfare [1]. Hybrid strategies, in the twenty-first century, involve the use of Information and Communication Technology (ICT) and AI tools to combine conventional and unconventional operations, amplifying the impact of these operations [1, 2, 3]. In the current context of hybrid operations, there are, presently, three major dimensions of hybrid strategic power, understood as the ability to achieve one's strategic goals through hybrid operations, and these are: The first type of power is enabled by social networks and the ability to use cyberspace for propaganda, disinformation, and viral campaigns in what constitutes a form of information-based warfare as well as for implementing cyberattacks that can disrupt different sectors as well as stealing (and possibly leaking) of critical data. The second type of power involves the use of AI, in particular ML tools, as support tools for different cyber operations that may, in turn, support hybrid strategies.