Fox News correspondent Alex Hogan reports from Kyiv, Ukraine on Russian attacks on civilian areas in the Donbas region this week on'America Reports.' Russia's naval headquarters for its Black Sea fleet in Ukraine's occupied Crimea was hit by a drone Saturday, a Russian official said. The Moscow installed governor of Sevastopol, Mikhail Razvozhayev, took to Telegram to confirm the hit and said a drone crashed into the roof of the building. There were no reported casualities. Razvozhayev first said the drone "flew into the roof" of the building and noted that Russian forces had not been able to down the strike. FILE - Russian Navy ships are docked in the Sevastopol bay on March 4, 2014.

Military drones are now everywhere. Of course, the capabilities of these machines are not the same, and the top-range models greatly outperform their lower-tier rivals. Simple remotely-operated robots and unmanned aerial vehicles are controlled by a human operator. Human decides what this military machine must do, even when conducting a simple reconnaissance operation, or dropping grenades through an open hatch on a tank's turret. But today we already have combat drones that can operate entirely on their own. This means they can recognize and engage their targets autonomously.

Many approaches have been proposed to deal with catastrophic forgetting (CF) in CIL. Most methods incrementally construct a single classifier for all classes of all tasks in a single head network. To prevent CF, a popular approach is to memorize a small number of samples from previous tasks and replay them during training of the new task. However, this approach still suffers from serious CF as the parameters learned for previous tasks are updated or adjusted with only the limited number of saved samples in the memory. This paper proposes an entirely different approach that builds a separate classifier (head) for each task (called a multi-head model) using a transformer network, called MORE. Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes. The model for the new task in MORE is trained to learn the classes of the task and also to detect samples that are not from the same data distribution (i.e., out-of-distribution (OOD)) of the task. This enables the classifier for the task to which the test instance belongs to produce a high score for the correct class and the classifiers of other tasks to produce low scores because the test instance is not from the data distributions of these classifiers. Experimental results show that MORE outperforms state-of-the-art baselines and is also naturally capable of performing OOD detection in the continual learning setting. Continual learning (CL) is a learning paradigm in which a system learns a sequence of tasks sequentially and accumulates the knowledge learned in the process (Chen & Liu, 2018). A main challenge of CL is how to adapt the existing knowledge in learning the new task without causing catastrophic forgetting (CF) (McCloskey & Cohen, 1989). CF refers to the phenomenon that the system forgets some of the previous knowledge after learning the new task due to modifications to model parameters learned for previous tasks. This paper proposes a novel method for the challenging CL setting of class incremental learning (CIL) (Rebuffi et al., 2017; van de Ven & Tolias, 2019). At any time, the system is expected to be able to classify a test instance x to one of the classes that have been learned so far without any information about the task it belongs to. The proposed approach is a memory-based method (also called a replay-based method). In this method, the system saves a small fraction of training samples in a memory buffer of a fixed size after learning each task.

As graph data becomes more ubiquitous, the need for robust inferential graph algorithms to operate in these complex data domains is crucial. In many cases of interest, inference is further complicated by the presence of adversarial data contamination. The effect of the adversary is frequently to change the data distribution in ways that negatively affect statistical and algorithmic performance. We study this phenomenon in the context of vertex nomination, a semi-supervised information retrieval task for network data. Here, a common suite of methods relies on spectral graph embeddings, which have been shown to provide both good algorithmic performance and flexible settings in which regularization techniques can be implemented to help mitigate the effect of an adversary. Many current regularization methods rely on direct network trimming to effectively excise the adversarial contamination, although this direct trimming often gives rise to complicated dependency structures in the resulting graph. We propose a new trimming method that operates in model space which can address both block structure contamination and white noise contamination (contamination whose distribution is unknown). This model trimming is more amenable to theoretical analysis while also demonstrating superior performance in a number of simulations, compared to direct trimming.

The security issue of mobile robots has attracted considerable attention in recent years. In this paper, we propose an intelligent physical attack to trap mobile robots into a preset position by learning the obstacle-avoidance mechanism from external observation. The salient novelty of our work lies in revealing the possibility that physical-based attacks with intelligent and advanced design can present real threats, while without prior knowledge of the system dynamics or access to the internal system. This kind of attack cannot be handled by countermeasures in traditional cyberspace security. To practice, the cornerstone of the proposed attack is to actively explore the complex interaction characteristic of the victim robot with the environment, and learn the obstacle-avoidance knowledge exhibited in the limited observations of its behaviors. Then, we propose shortest-path and hands-off attack algorithms to find efficient attack paths from the tremendous motion space, achieving the driving-to-trap goal with low costs in terms of path length and activity period, respectively. The convergence of the algorithms is proved and the attack performance bounds are further derived. Extensive simulations and real-life experiments illustrate the effectiveness of the proposed attack, beckoning future investigation for the new physical threats and defense on robotic systems.

A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use cases. However, running user studies is challenging and costly, and consequently each study typically only evaluates a limited number of different settings, e.g., studies often only evaluate a few arbitrarily selected explanation methods. To address these challenges and aid user study design, we introduce Use-Case-Grounded Simulated Evaluations (SimEvals). SimEvals involve training algorithmic agents that take as input the information content (such as model explanations) that would be presented to each participant in a human subject study, to predict answers to the use case of interest. The algorithmic agent's test set accuracy provides a measure of the predictiveness of the information content for the downstream use case. We run a comprehensive evaluation on three real-world use cases (forward simulation, model debugging, and counterfactual reasoning) to demonstrate that SimEvals can effectively identify which explanation methods will help humans for each use case. These results provide evidence that SimEvals can be used to efficiently screen an important set of user study design decisions, e.g.

Te reo M\=aori (referred to as M\=aori), New Zealand's indigenous language, is under-resourced in language technology. M\=aori speakers are bilingual, where M\=aori is code-switched with English. Unfortunately, there are minimal resources available for M\=aori language technology, language detection and code-switch detection between M\=aori-English pair. Both English and M\=aori use Roman-derived orthography making rule-based systems for detecting language and code-switching restrictive. Most M\=aori language detection is done manually by language experts. This research builds a M\=aori-English bilingual database of 66,016,807 words with word-level language annotation. The New Zealand Parliament Hansard debates reports were used to build the database. The language labels are assigned using language-specific rules and expert manual annotations. Words with the same spelling, but different meanings, exist for M\=aori and English. These words could not be categorised as M\=aori or English based on word-level language rules. Hence, manual annotations were necessary. An analysis reporting the various aspects of the database such as metadata, year-wise analysis, frequently occurring words, sentence length and N-grams is also reported. The database developed here is a valuable tool for future language and speech technology development for Aotearoa New Zealand. The methodology followed to label the database can also be followed by other low-resourced language pairs.

Community nurses could soon be turning up to appointments wearing a pair of rather impressive hi-tech glasses. Their patients may be a little daunted, but it is hoped the glasses will deal with much of the admin associated with each visit. This would allow the nurses – who typically spend more than half of their day filling out forms and manually inputting data – to spend more time caring for and talking to the patients. The glasses will help them create a record of the visit, book further appointments, consult live with colleagues such as doctors, plan their day and even determine how well a wound is healing. The technology, funded by NHS England, will be tried out in Northern Lincolnshire and Goole from next week.

Russia's internet watchdog Roskomnadzor is developing a neural network that will use artificial intelligence to scan websites for prohibited information. Called "Oculus," the automatic scanner will analyze URLs, images, videos, and chats on websites, forums, social media, and even chat/messenger channels to locate material that should be redacted or taken down. Examples of information targeted by Oculus include homosexuality "propaganda," instructions on manufacturing weapons or drugs, and misinformation that discredits official state and army sources. The system will also look for calls of mass protests, expressions of disrespect for the state, and even "signs" of extremism and terrorism. The real-time scanning capacity of Oculus will be 200,000 images per day, or about 2.3 images per second, for which the vendor, Eksikyushn RDC LLC, will use 48 servers with powerful GPUs.

Shortly after the game's PC release, a modder going by the handle Mike Hawk (probably don't try saying it out loud) released a mod called "Non-Newtownian New York." According to its creator, the mod replaced "Newton's Prism's artifacts with the stars and stripes." This was a roundabout way of saying it turned Pride flags into United States flags. As many have pointed out, "Spider-Man" already includes a plethora of U.S. flags even without mods, and Spider-Man -- given his habit of standing up for the oppressed -- has frequently been associated with progressive causes.