Logitech's popular Harmony universal remotes have long been the go-to solution for tech-savvy nerds who want to replace the bounty of ugly rectangles littering their coffee tables with a single, all-powerful option. But universal remotes are still pretty complex on their own, with dozens of buttons and, in some cases, LCD screens. You're basically swapping several remotes for something that looks like it belongs in one of NASA's Mission Control Centers. Now, there's something simpler: the Harmony Express, a compact universal remote that replaces a slew of buttons with Amazon Alexa voice controls. The $250 Express isn't meant to replace the Harmony Elite, which Logitech released back in 2015 and is still one of the best high-end universal remotes around.

Robot vacuums today are not the clunky furniture destroyers from yesteryear. Modern automated floor cleaners now connect to the internet, which allows you to control your robot with smart apps, as well as with digital assistants like Alexa and Google Home. When smart connectivity first debuted, our testing showed it was a bit of a gimmick. However, over time, smart technology has evolved to the point it's a major plus when done right. Recent smart robot vacuums have features like onboard cameras so they can act like security cameras as well as floor cleaners.

Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. Through extensive experiments on several public benchmarks and one large-scale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

Smart bulbs help you automate and fine-tune your lighting situation, and today you can get a four-pack of our favorite white LED bulb, the Philips Hue White Ambiance A19, for $40 on Amazon. That's down from a list price of $50 and the lowest we've ever seen it. These LED bulbs provide detailed control options, allowing you to personalize the dim, set schedules, turn lights off and on from anywhere, and more using the Philips Hue app. You can also control the bulbs using your voice when you connect them with an Amazon Echo, Google Home, or Apple HomeKit. And you won't have to replace them often--each bulb lasts over 25,000 hours, or 20 years.

A new challenger could be approaching Apple's iconic AirPods (pictured above). Microsoft is developing a pair of Surface-branded wireless earbuds, according to Brad Sams' oft-reliable sources at Thurrott.com. Microsoft surprised the world by releasing the surprisingly good Surface Headphones last October. The sleek, premium-priced $350 headset features an intuitive control scheme and some wickedly good noise cancellation chops, courtesy of four active mics that keep tabs on the sounds around you. "Spin the noise cancellation dial on Microsoft's new cans, and the world fades away," we wrote at the time. Of course, you could also use the Surface Headphones to converse with Microsoft's Cortana digital assistant via its mobile app.

Spotify, Pandora and YouTube are currently the top games in town for listening to online music for free, via ads. Possibly add Amazon to the list. Billboard reports that Amazon looks to launch a similar service, which would be available only if you ask Alexa. The songs could be accessed via the Echo connected speakers, which are made by Amazon. Amazon currently offers some 2 million songs available free to Echo owners who also pay $119 yearly to subscribe to the company's Prime for expedited shipping and online music, movies and TV.

The number of recorded sexual offences involving online dating sites and apps has almost doubled in the last four years, police figures suggest. Offences where a dating site was mentioned in a police report increased from 156 in 2015, to 286 last year, according to figures from 23 of the 43 forces in England and Wales. The Online Dating Association said apps try to protect users from harm. But the National Police Chiefs' Council said firms had a duty to do more. The figures reveal that between 2015 and 2018 there were a total of 2,029 recorded offences - including sexual offences - where an online dating website or app was mentioned in a police report. In 2015, 329 offences were recorded, compared to 658 recorded offences last year.

Ranking is a core task in E-commerce recommender systems, which aims at providing an ordered list of items to users. Typically, a ranking function is learned from the labeled dataset to optimize the global performance, which produces a ranking score for each individual item. However, it may be sub-optimal because the scoring function applies to each item individually and does not explicitly consider the mutual influence between items, as well as the differences of users' preferences or intents. Therefore, we propose a personalized context-aware re-ranking model for E-commerce recommender systems. The proposed re-ranking model can be easily deployed as a follow-up modular after ranking by directly using the existing feature vectors of ranking. It directly optimizes the whole recommendation list by employing a transformer structure to efficiently encode the information of all items in the list. Specifically, the Transformer applies a self-attention mechanism that directly models the global relationships between any pair of items in the whole list. Besides, we introduce the personalized embedding to model the differences between feature distributions for different users. Experimental results on both offline benchmarks and real-world online E-commerce systems demonstrate the significant improvements of the proposed re-ranking model.

Artificial intelligence (AI) changes the way we go about our everyday lives. Consider Apple's line of mobile devices with Siri. And think about Amazon's smart home products featuring Alexa. They make us comfortable interacting with a virtual assistant. These forms of AI make our lives easier and help us perform hands-free tasks.

Sales of smart speakers are soaring despite some people's concerns over privacy, with Amazon's Alexa leading the charge into homes in various Echo devices and Google's Home and Assistant snapping at its heels. They come in various shapes, sizes and prices, but if you just want to dip your toe into the burgeoning voice-powered world, what's the cheapest way to get Alexa or Google Assistant into your home? Voice assistants don't actually need a dedicated speaker to work. If you have a modern smartphone chances are you either already have Google Assistant, if you have an Android phone, or can install the app on an iPhone. The same goes for Amazon's Alexa, which can even be set as the default voice assistant on an Android phone.