The Portal Plus is an expensive device with a $349 price tag that belies its capabilities. Although the Portal Plus boasts a big screen and some fun tools, it's far more limited than, say, the current-generation Amazon Echo Show 10 and Google Nest Hub Max. In fact, the big screen is arguably the sole reason to choose the Portal Plus over Facebook's $199 Portal Go, a nearly identical device save for its 10-inch display and battery-powered portability. Whether or not you'll be truly satisfied with either one, though, depends on what you want--and whether you have a Facebook or WhatsApp account, one of which is required to use any Portal. The Portal Plus' base is also its speaker.

Since the 1970s, the story of the television is one of conquest as it swallowed more and more space in our living rooms. Owning a set wasn't good enough, we needed a VCR, BetaMax or LaserDisc player to lurk on a nearby shelf. A decade later, a console or home computer would take its place in the orbit of the TV, followed not long after by the cable box. And, in the DVD age, people would take advantage of the affordability of rudimentary 5.1 surround sound to add in an AV Receiver, or Amp, to that ever-growing TV cabinet. And, as TVs got flatter and wider, their integral speakers stopped being up to the job so much that a dedicated sound bar was essential. Throw in a streaming stick or puck, and our TVs have become ecosystems of their own, no longer lurking but dominating our living rooms. Sky Glass, then, is a reaction against this sprawl, an all-in-one TV, set-top-box and soundbar that promises to eliminate the clutter. Hell, Sky Glass even has its own games pre-installed, although you'll still need to bring your console along for the serious stuff. It's also the first true-blue Sky device that doesn't need a satellite dish for connection, instead delivering all of its content through the internet.

Epam Systems' Sam Rehman discusses how machine learning can change the cybersecurity landscape for the better but also comes with challenges.

We have daily access to it right at our fingertips, and soon enough it is going to take over many tedious tasks in agriculture, like weeding. Artificial intelligence is the way of the future, only getting better by the minute. "This is a an AI based machine learning platform that has a very good ability to take pictures of plants or the crops we want to keep and open up mechanical blades around the plants we want to keep in close after the plant and cultivate and remove weeds," said Ben Palone, senior technical product and product manager at Farmwise. High-tech cameras are the eyes of the robot, and the brain is pretty close to what a farmer would be tasked to do. "This is all based on digital camera technology. We take the pictures and then the pictures are fed into a computer, and the computer analyzes the pictures and decides what to do on the field after," said Tony Koselka, co-founder of Vision Robotics.

Over the past decade, we have seen exponential growth in online content fueled by social media platforms. Data generation of this scale comes with the caveat of insurmountable offensive content in it. The complexity of identifying offensive content is exacerbated by the usage of multiple modalities (image, language, etc.), code mixed language and more. Moreover, even if we carefully sample and annotate offensive content, there will always exist significant class imbalance in offensive vs non offensive content. In this paper, we introduce a novel Code-Mixing Index (CMI) based focal loss which circumvents two challenges (1) code mixing in languages (2) class imbalance problem for Dravidian language offense detection. We also replace the conventional dot product-based classifier with the cosine-based classifier which results in a boost in performance. Further, we use multilingual models that help transfer characteristics learnt across languages to work effectively with low resourced languages. It is also important to note that our model handles instances of mixed script (say usage of Latin and Dravidian - Tamil script) as well. Our model can handle offensive language detection in a low-resource, class imbalanced, multilingual and code mixed setting.

Although the recent advancement in generative models brings diverse advantages to society, it can also be abused with malicious purposes, such as fraud, defamation, and fake news. To prevent such cases, vigorous research is conducted to distinguish the generated images from the real images, but challenges still remain to distinguish the unseen generated images outside of the training settings. Such limitations occur due to data dependency arising from the model's overfitting issue to the training data generated by specific GANs. To overcome this issue, we adopt a self-supervised scheme to propose a novel framework. Our proposed method is composed of the artificial fingerprint generator reconstructing the high-quality artificial fingerprints of GAN images for detailed analysis, and the GAN detector distinguishing GAN images by learning the reconstructed artificial fingerprints. To improve the generalization of the artificial fingerprint generator, we build multiple autoencoders with different numbers of upconvolution layers. With numerous ablation studies, the robust generalization of our method is validated by outperforming the generalization of the previous state-of-the-art algorithms, even without utilizing the GAN images of the training dataset.

Recommender systems are software applications that help users find items of interest in situations of information overload in a personalized way, using knowledge about the needs and preferences of individual users. In conversational recommendation approaches, these needs and preferences are acquired by the system in an interactive, multi-turn dialog. A common approach in the literature to drive such dialogs is to incrementally ask users about their preferences regarding desired and undesired item features or regarding individual items. A central research goal in this context is efficiency, evaluated with respect to the number of required interactions until a satisfying item is found. This is usually accomplished by making inferences about the best next question to ask to the user. Today, research on dialog efficiency is almost entirely empirical, aiming to demonstrate, for example, that one strategy for selecting questions is better than another one in a given application. With this work, we complement empirical research with a theoretical, domain-independent model of conversational recommendation. This model, which is designed to cover a range of application scenarios, allows us to investigate the efficiency of conversational approaches in a formal way, in particular with respect to the computational complexity of devising optimal interaction strategies. Through such a theoretical analysis we show that finding an efficient conversational strategy is NP-hard, and in PSPACE in general, but for particular kinds of catalogs the upper bound lowers to POLYLOGSPACE. From a practical point of view, this result implies that catalog characteristics can strongly influence the efficiency of individual conversational strategies and should therefore be considered when designing new strategies. A preliminary empirical analysis on datasets derived from a real-world one aligns with our findings.

LOS ALAMOS, N.M., Nov. 10, 2021--Researchers at Los Alamos National Laboratory are applying machine learning algorithms to help interpret massive amounts of ground deformation data collected with Interferometric Synthetic Aperture Radar (InSAR) satellites; the new algorithms will improve earthquake detection. "Applying machine learning to InSAR data gives us a new way to understand the physics behind tectonic faults and earthquakes," said Bertrand Rouet-Leduc, a geophysicist in Los Alamos' Geophysics group. New satellites, such as the Sentinel 1 Satellite Constellation and the upcoming NISAR Satellite, are opening a new window into tectonic processes by allowing researchers to observe length and time scales that were not possible in the past. However, existing algorithms are not suited for the vast amount of InSAR data flowing in from these new satellites, and even more data will be available in the near future. In order to process all of this data, the team at Los Alamos developed the first tool based on machine learning algorithms to extract ground deformation from InSAR data, which enables the detection of ground deformation automatically--without human intervention--at a global scale.

Every week, I help people like you on my national radio show with their technology or digital life issues. Sometimes, the answer is simple. I recommend a great way to get something done online, give a shopping recommendation, or share my tech wisdom. Other times, the issue is harder to pinpoint. Here's a common question I get: "A friend called and said they got a strange email from me that I don't remember sending.

"What projects can I do with machine learning?" We often get asked this question a lot from beginners getting started with machine learning. ProjectPro industry experts recommend that you explore some exciting, cool, fun, and easy machine learning project ideas across diverse business domains to get hands-on experience on the machine learning skills you've learned.