Its simplicity also raises many practical and theoretical questions about the task-relations it can exploit and the settings in which it can succeed.

Indeed the same story holds for images stored on users' devices, which is more consistent with

Its simplicity also raises many practical and theoretical questions about the task-relations it can exploit and the settings in which it can succeed.

Network modernization is a key component of digital transformation initiatives for organizations looking to achieve better business outcomes. With that in mind, Aruba has announced its new Aruba Edge Services Platform with AIOps capabilities designed to reduce the time IT professionals spend on manual tasks such as network troubleshooting, performance tuning and Zero Trust/SASE security enforcement. As part of Aruba's growing family of AIOps solutions, these new capabilities aim to supplement overtaxed IT teams as they grapple with increasing network complexity and the rapid growth of IoT. For the first time, AIOps can be utilized for not just network troubleshooting but also performance optimization and critical security controls, Aruba said. With the growth of hybrid work, new user engagement models and challenges resulting from the Great Resignation and widening skills gaps, IT teams must find ways to achieve greater efficiencies and do away with time-intensive manual processes, the company said.

Ere Santos remembers that he once had to animate a fight between his character, the sidekick, and the hero of the film. Luckily, the hero's animator sat next to Mr Santos. Much like their creations, the two colleagues went to battle on how the interaction should work. Instead of drawing, these feature film animators create computer simulations based on physics. Mr Santos likens it to making a puppet that the computer will bring to life.

Figure 1: Illustration of the meta-learning process as applied to the task of personalized next-word prediction. Here each mobile device corresponds to a different next-word prediction task, with the test-task not seen during meta-training (Step 1). In the classical machine learning setup, we aim to learn a single model for a single task given many training samples from the same distribution. However, in many practical applications, we are in fact exposed to several distinct yet related tasks that have only a few examples each. Because the data now come from different training distributions, simply learning a single global model, e.g., via stochastic gradient descent (SGD), may result in poor performance on each task.

Juniper Networks rolled out Mist's artificial intelligence (AI) engine across wired and wireless networks today to kick off its annual Nxtwork event. It's the first step in what Juniper calls the "AI-driven enterprise" that will use AI and automation to troubleshoot and self-correct across the entire IT environment. "For that we mean wireless access, wired access, and ultimately data centers as well as SD-WAN with a security overlay on top of that," said Jeff Aaron, VP of enterprise marketing at Juniper Networks. Juniper acquired wireless LAN startup Mist Systems for $405 million earlier this year. In addition to the wireless technology, the deal gave Juniper an in-house AI engine.

Hewlett Packard Enterprise (HPE) announced new edge solutions, research labs and programs to simplify and accelerate Intelligent Edge adoption, enabling customers to create unique digital experiences and leverage analytics and machine learning to adapt to changes in real-time. These offerings and programs include enhancements to Aruba Central, its cloud-based platform that unifies network management, AI-powered analytics, user-centric service assurance and security for wired, wireless and WAN at the edge. Integrations and new turnkey edge-to-cloud solutions, delivered with ABB, Microsoft and PTC, enabling real-time intelligence and control in industrial environments, and Intelligent Edge and IoT Center of Excellence (CoE) and Labs, part of Hewlett Packard Labs, to develop and commercialize new capabilities and technologies that accelerate customers' and partners' Intelligent Edge journey. Research suggests that over the next decade, the Internet of Things (IoT) and related data growth has an economic potential of up to $11 trillion per year. To capture this potential, organizations need to implement an Intelligent Edge, an architecture that is fully connected, secured, distributed and autonomous.

We build a theoretical framework for understanding practical meta-learning methods that enables the integration of sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geometric structure. We use our theory to modify several popular meta-learning algorithms and improve their training and meta-test-time performance on standard problems in few-shot and federated deep learning.