The application of machine learning techniques to large-scale personalized recommendation problems is a challenging task. Such systems must make sense of enormous amounts of implicit feedback in order to understand user preferences across numerous product categories. This paper presents a deep learning based solution to this problem within the collaborative filtering with implicit feedback framework. Our approach combines neural attention mechanisms, which allow for context dependent weighting of past behavioral signals, with representation learning techniques to produce models which obtain extremely high coverage, can easily incorporate new information as it becomes available, and are computationally efficient. Offline experiments demonstrate significant performance improvements when compared to several alternative methods from the literature. Results from an online setting show that the approach compares favorably with current production techniques used to produce personalized product recommendations.

Google is cramming Assistant into everything from headphones to a pressure cooker as it inches toward getting the smart helper into a billion devices. Aside from the weirder collabs (Assistant in a shower anyone?) one of the places the AI would actually be helpful is in your car, especially if you don't want to fork out for an Android Auto infotainment system. To that end, Google is teaming up with accessories-maker Anker -- which is also bringing Alexa to older vehicles inside its upcoming $50 Bluetooth charger -- on a new in-car receiver that plays nice with the digital brainiac. The new "Roav Bolt" is a small, unassuming device that connects your phone to your vehicle's stereo to let you talk to Assistant, allowing you to keep your eyes glued to the road and your phone in your pocket (or with the kids in the backseat). Just plug the Bolt into your car's lighter socket and hook up your phone via Bluetooth or AUX to play music, get directions, or answer the phone through the speakers.

Razer is about to make it considerably easier to control your RGB-lit gaming rig. The company has unveiled plans to introduce Amazon Alexa control through its Synapse 3 software, letting you voice control devices that support its Chroma Connected Devices Program through Razer headsets and microphones. That includes legions of Razer's own mice, keyboards and audio devices, but it also includes PC cases, cooling fans, motherboards and other peripherals. Want to turn your setup blood red for a round of Doom? You'd just have to ask Alexa to change your lighting profile.

Thousands of hacked Chromecasts and smart TVs are hijacked to show this image. More than 5,500 exposed smart TVs, Chromecast streamers and Google Home devices have been commandeered in the name of YouTube mega-star PewDiePie. Hacker Giraffe, the same pseudonymous person who forced thousands of exposed printers last year to churn out pages saying "Subscribe to PewDiePie," has his set sight on smart devices to promote the Swedish YouTube star's channel. Not that PewDiePie needs much help. He has the top-ranked channel with nearly 79.5 million subscribers.

From Uber's advanced computer vision system to Netflix's innovative recommendation algorithm, machine learning technologies are nearly omnipresent in our society. They filter our emails, personalize our newsfeeds, update our GPS systems, and drive our personal assistants. However, despite the fact that such technologies are leading a revolution in artificial intelligence, some would contend that these machine learning systems aren't truly intelligent. The argument, in its most basic sense, centers on the fact that machine learning evolved from theories of pattern recognition and, as such, the capabilities of such systems generally extend to just one task and are centered on making predictions from existing data sets. AI researchers like Rodney Brooks, a former professor of Robotics at MIT, argue that true reasoning, and true intelligence, is several steps beyond these kinds of learning systems.

A link has been posted to your Facebook feed. LAS VEGAS – Deep in a battle with Amazon's Alexa for the dominant voice companion, Google Assistant will be on 1 billion devices by the end of January, the company said at CES. That includes Android and iOS smartphones, display units like Google Home Hub, speakers like Google Home, plus TVs, headphones, watches and more. Google said the Assistant (otherwise known as "Hey" or "OK Google") is available in 30 languages and 80 countries, up from eight languages and 14 countries in 2017. Google's signs are all over CES, touting the "Google Assistant," Google's answer to Amazon's Alexa.

Whirlpool has already made a slew of announcements here at CES, but it's not quite done yet. Today, the appliance giant is unveiling its first-ever smart countertop oven, courtesy of W Labs, its innovation incubator. Something of a June competitor, the Whirlpool Smart Countertop Oven is able to identify foods and then choose the appropriate temperatures and algorithms to cook them to perfection. There's a camera inside so you can monitor what's going on with a companion app, a smart food thermometer, and of course cooking status notifications as well. It even has a scan-to-cook tech that will be incorporated into select frozen foods. Last but not least, it also has voice activation courtesy of Google Assistant or Amazon's Alexa, so you can just command it to set the timer or change the temperature.

Brilliant, a smart home hub that plugs into existing light-switch ports, already works with Amazon Alexa, Google Assistant, Nest, Philips Hue, August smart locks and a whole bunch of other home accessories. Now, it's adding Apple HomeKit-enabled devices to the things you can control using its touchscreen panel. The integration also allows you to control lights connected to the hub by voice using Siri on iPhones, iPads, Apple Watches, HomePods and Macs. You can also control those lights using the Apple Home app. The company first introduced its product back in CES 2018 and made it available for sale in September.

Among the mountains of sexy technology on the market, it's fair to say that hearing aids don't feature too highly when it comes to innovation and aspirational living. But as Starkey Hearing Technologies demonstrated with its Livio AI device last year, there's a lot to be done in this field -- and now its smart hearing aid has gotten even smarter. Granted, not many people view hearing aids as smart devices -- they are traditionally the preserve of the elderly, and therefore not particularly synonymous with The Internet of Things. But new updates to the device which already boasted a host of useful features -- such as Alexa voice control and built-in language translation -- are set to completely reimagine the concept of the hearing aid. Announced at CES, the Livio AI device now comes with fall detection, heart rate measurement and a built-in virtual assistant.

Leviton is expanding its range of smart home switches and outlets with a new Wi-Fi dimmer switch with Amazon Alexa built in. The Decora Voice Dimmer will allow home owners to control their lights with their voice, and it works with all the other things that Amazon Alexa supports. For example, users will be able to say "Alexa, dim the lights to 60 percent," or "Alexa, turn off the kitchen light." Leviton already sells Wi-Fi light switches in the Decora range and the new dimmer can be integrated into routines and schedules through the My Leviton control app. Because the switches are all networked, it's also possible to issue a single command--"Alexa, turn off the lights"--to control all the lights in every room connected through a Wi-Fi Decora switch.