The Drone Swarm Search project is an environment, based on PettingZoo, that is to be used in conjunction with multi-agent (or single-agent) reinforcement learning algorithms. It is an environment in which the agents (drones), have to find the targets (shipwrecked people). The agents do not know the position of the target and do not receive rewards related to their own distance to the target(s). However, the agents receive the probabilities of the target(s) being in a certain cell of the map. The aim of this project is to aid in the study of reinforcement learning algorithms that require dynamic probabilities as inputs.

With the growing capabilities and pervasiveness of AI systems, societies must collectively choose between reduced human autonomy, endangered democracies and limited human rights, and AI that is aligned to human and social values, nurturing collaboration, resilience, knowledge and ethical behaviour. In this chapter, we introduce the notion of self-reflective AI systems for meaningful human control over AI systems. Focusing on decision support systems, we propose a framework that integrates knowledge from psychology and philosophy with formal reasoning methods and machine learning approaches to create AI systems responsive to human values and social norms. We also propose a possible research approach to design and develop self-reflective capability in AI systems. Finally, we argue that self-reflective AI systems can lead to self-reflective hybrid systems (human + AI), thus increasing meaningful human control and empowering human moral reasoning by providing comprehensible information and insights on possible human moral blind spots.

Maneuver decision-making is the core of unmanned combat aerial vehicle for autonomous air combat. To solve this problem, we propose an automatic curriculum reinforcement learning method, which enables agents to learn effective decisions in air combat from scratch. The range of initial states are used for distinguishing curricula of different difficulty levels, thereby maneuver decision is divided into a series of sub-tasks from easy to difficult, and test results are used to change sub-tasks. As sub-tasks change, agents gradually learn to complete a series of sub-tasks from easy to difficult, enabling them to make effective maneuvering decisions to cope with various states without the need to spend effort designing reward functions. The ablation studied show that the automatic curriculum learning proposed in this article is an essential component for training through reinforcement learning, namely, agents cannot complete effective decisions without curriculum learning. Simulation experiments show that, after training, agents are able to make effective decisions given different states, including tracking, attacking and escaping, which are both rational and interpretable.

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be beneficial for a range of tasks, there is not a clear understanding yet of the reasons for this effect. In this work, we examine the relationship between pretrained vision transformers and the corresponding finetuned versions on several benchmark datasets and tasks. We present new metrics that specifically investigate the degree to which invariances learned by a pretrained model are retained or forgotten during finetuning. Using these metrics, we present a suite of empirical findings, including that pretraining induces transferable invariances in shallow layers and that invariances from deeper pretrained layers are compressed towards shallower layers during finetuning. Together, these findings contribute to understanding some of the reasons for the successes of pretrained models and the changes that a pretrained model undergoes when finetuned on a downstream task. In recent years much progress in deep learning has been driven by the reuse of models that were pretrained on large amounts of data. This is usually achieved by finetuning their parameters using a smaller amount of data from a target downstream task. This pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, and has become commonplace across many areas of machine learning, including natural language processing (Howard & Ruder, 2018) and computer vision (Girshick et al., 2014). While pretraining is empirically observed to be beneficial for a range of tasks, there is not a clear understanding yet of the reasons for this effect. Previous work has empirically examined various conditions for pretraining and found that for a given budget of pre-training images, training with fewer classes, but more images per class performs better (Huh et al., 2016). Pretraining has also been posited to elicit an accelerated convergence during finetuning (Kornblith et al., 2019b), suggesting that during pretraining, models learn transferable representations, particularly when the finetuning task domain is similar to the pretraining task.

Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a few labeled target-domain data and a well-trained source-domain classifier (i.e., a source hypothesis), for the additional information of the highly-compatible unlabeled data. However, the generated data of the existing methods are extremely similar or even the same. The strong dependency among the generated data will lead the learning to fail. In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC). Specifically, DEG-Net will generate data via minimizing the HSIC value (i.e., maximizing the independence) among the semantic features of the generated data. By DEG-Net, the generated unlabeled data are more diverse and more effective for addressing the FHA problem. Experimental results show that the DEG-Net outperforms existing FHA baselines and further verifies that generating diverse data plays a vital role in addressing the FHA problem

To realize the potential benefits and mitigate potential risks of AI, it is necessary to develop a framework of governance that conforms to ethics and fundamental human values. Although several organizations have issued guidelines and ethical frameworks for trustworthy AI, without a mediating governance structure, these ethical principles will not translate into practice. In this paper, we propose a multilevel governance approach that involves three groups of interdependent stakeholders: governments, corporations, and citizens. We examine their interrelationships through dimensions of trust, such as competence, integrity, and benevolence. The levels of governance combined with the dimensions of trust in AI provide practical insights that can be used to further enhance user experiences and inform public policy related to AI.

Russia has launched a wave of drone attacks on Kyiv and nearby regions for a second consecutive night, with air defence systems engaged in repelling the attack, a Ukraine military official said. "The air raid alert is on! Air defence systems engaged in the region on approach to Kyiv," Serhiy Popko, head of the military administration for the Ukrainian capital, said on the Telegram messaging app early on Wednesday morning. The Kyiv military administration urged people to stay in shelters until the raids were over. Witnesses in Kyiv heard blasts resembling the sound of air defence systems intercepting air objects, the Reuters news agency reported.

The head of the UK's financial regulator is to warn that banks, investors and insurers will have to ramp up their spending to combat scammers using artificial intelligence to commit fraud. Nikhil Rathi, the chief executive of the Financial Conduct Authority (FCA), will say that there are risks of "cyber fraud, cyber-attacks and identity fraud increasing in scale and sophistication and effectiveness" as artificial intelligence (AI) becomes more widespread, in a speech in London on Wednesday. Rapid advances in the sophistication of generative AI by companies such as OpenAI and Midjourney have set companies scrambling to work out how to use the technology to improve productivity. The technology has also prompted concerns over the ease with which users can fake language, audio and video. The prime minister, Rishi Sunak, is hoping to make the UK a centre for the regulation of AI.

Kurt "The CyberGuy" Knutsson describes a situation in which a viewer was hacked and reveals what steps you can take to avoid this from happening to you. In today's digital chorus, your voice is the newest solo. It's not just for singing in the shower or whispering sweet nothings anymore. However, just as we're crooning over the idea of voice authentication, hackers are hitting a high note, mastering the art of mimicking it. CLICK TO GET KURT'S FREE CYBERGUY NEWSLETTER WITH SECURITY ALERTS, QUICK TIPS, TECH REVIEWS AND EASY HOW-TO'S TO MAKE YOU SMARTER When enrolling in voice authentication, you are asked to repeat a specific phrase in your own voice.

A federal judge has handed Microsoft a major victory by declining to block its looming $69 billion takeover of video game company Activision Blizzard. Regulators are seeking to ax the deal because they say it will hurt competition. U.S. District Judge Jacqueline Scott Corley said in a ruling that the "FTC has not shown a likelihood it will prevail on its claim this particular vertical merger in this specific industry may substantially lessen competition. Microsoft appeared to have the upper hand in a 5-day San Francisco court hearing that ended late last month. The proceeding showcased testimony by Microsoft Chief Executive Officer Satya Nadella and longtime Activision Blizzard CEO Bobby Kotick, who both pledged to keep Activision's blockbuster game Call of Duty available to people who play it on consoles -- particularly Sony's PlayStation -- that compete with Microsoft's Xbox. Read More: Why Microsoft's Satya Nadella Doesn't Think Now Is the Time to Stop on AI "Our merger will benefit consumers and workers.