The design of effective online caching policies is an increasingly important problem for content distribution networks, online social networks and edge computing services, among other areas. This paper proposes a new algorithmic toolbox for tackling this problem through the lens of optimistic online learning. We build upon the Follow-the-Regularized-Leader (FTRL) framework which is developed further here to include predictions for the file requests, and we design online caching algorithms for bipartite networks with fixed-size caches or elastic leased caches subject to time-average budget constraints. The predictions are provided by a content recommendation system that influences the users viewing activity, and hence can naturally reduce the caching network's uncertainty about future requests. We prove that the proposed optimistic learning caching policies can achieve sub-zero performance loss (regret) for perfect predictions, and maintain the best achievable regret bound $O(\sqrt T)$ even for arbitrary-bad predictions. The performance of the proposed algorithms is evaluated with detailed trace-driven numerical tests.

Empirical results in software engineering have long started to show that findings are unlikely to be applicable to all software systems, or any domain: results need to be evaluated in specified contexts, and limited to the type of systems that they were extracted from. This is a known issue, and requires the establishment of a classification of software types. This paper makes two contributions: the first is to evaluate the quality of the current software classifications landscape. The second is to perform a case study showing how to create a classification of software types using a curated set of software systems. Our contributions show that existing, and very likely even new, classification attempts are deemed to fail for one or more issues, that we named as the `antipatterns' of software classification tasks. We collected 7 of these antipatterns that emerge from both our case study, and the existing classifications. These antipatterns represent recurring issues in a classification, so we discuss practical ways to help researchers avoid these pitfalls. It becomes clear that classification attempts must also face the daunting task of formulating a taxonomy of software types, with the objective of establishing a hierarchy of categories in a classification.

We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields or signed distance fields which can only model closed 3D surfaces, our approach is not restricted to any type of topology. Being different from the existing unsigned distance fields, our framework does not suffer from any surface ambiguity. In addition, our RangeUDF can jointly estimate precise semantics for continuous surfaces. The key to our approach is a range-aware unsigned distance function together with a surface-oriented semantic segmentation module. Extensive experiments show that RangeUDF clearly surpasses state-of-the-art approaches for surface reconstruction on four point cloud datasets. Moreover, RangeUDF demonstrates superior generalization capability across multiple unseen datasets, which is nearly impossible for all existing approaches.

Solicitous is the Best Indian robotics company for applied AI and robotics technology to various environments, including home, school, healthcare, industrial, aerial drones, and retail. Solicitous is a provider of AI-related customized software development and associated IT services for advanced robotics applications with artificial intelligence and a machine learning expert team. Solicitous works with global manufacturers for different types of robots. The company creates state-of-the-art robotics products that meet customers' exacting requirements, solving robotics problems using the latest cutting-edge technologies. Offering innovative products to help customers run their businesses more effectively and save costing, solicitous delivers the solutions which allow today's advanced personal robots to integrate into all aspects of our everyday lives, both at home and in the workplace.

There's nobody better at persecuting a war than the United States -- we've got the the best-equipped and biggest-budgeted fighting force on the face of the Earth. But does carrying the biggest stick still constitute a strategic advantage if the mere act of possessing it seems to make us more inclined to use it? In his latest book, Future Peace (sequel to 2017's Future War) Dr. Robert H. Latiff, Maj Gen USAF (Ret), explores how the American military's increasing reliance on weaponized drones, AI and Machine Learning systems, automation and similar cutting-edge technologies, when paired with an increasingly rancorous and often outright hostile global political environment, could create the perfect conditions for getting a lot of people killed. In the excerpt below, Dr. Latiff looks at the impact that America's lionization of its armed forces in the post-Vietnam era and new access to unproven tech have on our ability to mitigate conflict and prevent armed violence. Published by University of Notre Dame Press.

Nowadays, there are outstanding strides towards a future with autonomous vehicles on our roads. While the perception of autonomous vehicles performs well under closed-set conditions, they still struggle to handle the unexpected. This survey provides an extensive overview of anomaly detection techniques based on camera, lidar, radar, multimodal and abstract object level data. We provide a systematization including detection approach, corner case level, ability for an online application, and further attributes. We outline the state-of-the-art and point out current research gaps.

In recent years, players within Canada's financial services industry, from banks to Fintech startups, have shown early and innovative adoption of artificial intelligence ("AI") and machine learning ("ML") within their organizations and services. With the ability to review and analyze vast amounts of data, AI algorithms and ML help financial services organizations improve operations, safeguard against financial crime, sharpen their competitive edge and better personalize their services. As the industry continues to implement more AI and build upon its existing applications, it should ensure that such systems are used responsibly and designed to account for any unintended consequences. Below we provide a brief overview of current considerations, as well as anticipated future shifts, in respect of the use of AI in Canada's financial services industry. At a high level, Canadian banks and many bank-specific activities are matters of federal jurisdiction.

LiveRamp is the leading data connectivity platform. We are committed to connecting the world's data safely and effectively, advancing innovation and empowering people to do good. Our platform powers customer experiences centered around the needs of real people, keeping the Internet open for all. We enable individuals around the world to connect with the brands and products they love. LiveRampers thrive on solving challenging problems for the good of humanity--and we're always looking for smart, kind, and creative people to help us get there.

Despite its technological benefits, Internet of Things (IoT) has cyber weaknesses due to the vulnerabilities in the wireless medium. Machine learning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. Advanced persistent threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys to fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth to bridge the state-of-the-art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents the well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion alongside the number of attacks types detected. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.

A large amount of patient-related information is collected by healthcare operators in their everyday activities, which span over a wide spectrum of medical processes, such as wellness check-ups or examinations at healthcare hospitals or medical offices, just to name a few. For instance, when a patient undergoes a medical examination for the first time, the physician usually creates a patient file including his medical history, current treatments, medications, diagnosis, and other relevant information [1]. Considering that disease diagnosis is crucial for health condition monitoring, it is natural to envisage that such large amount of data can be profitably used to guide data-driven disease classification tasks in the quest for early and accurate diagnoses, taking care of the complex interactions among clinical, biological, and pathological variables. Indeed, with the aim of identifying the best services and treatments for the patients, recent advances in medicine have proposed various models for personalized, predictive, and preventive medicine that make use of electronic health records (EHRs) and high-dimensional omics data [2]. However, accessing and using EHRs and omics data can be rather challenging in practice, because they are heterogeneous and usually stored in different data formats.