If you drive an electric car and would rather not venture into the garage (or wade through a phone app) to start charging, you can now rest easy. ChargePoint has introduced Alexa support to its Home system, giving you voice control over your EV charging. You can start charging, stop charging or find out whether you're plugged in just by talking to a device like an Echo speaker. If you have Nest hardware, you can link charging to multiple parts of your home. And if you top up at ChargePoint stations away from home, you can check your balance or see how much you've spent on electricity so far.

Poisson matrix factorization (PF) is a nonnegative matrix factorization (NMF) model (Lee and Seung, 1999) often used for recommender systems (Ma et al., 2011; Gopalan et al., 2015), text information retrieval (Canny, 2004; Buntine and Jakulin, 2006) or dictionary learning for image processing (Cemgil, 2009). The data is assumed to be drawn from the Poisson distribution making it specially well suited for count/integer-valued data. Since the Netflix Prize (Bennett et al., 2007), collaborative filtering (CF) has been giving the state-of-the-art results for recommender systems. CF exploits data relating users to items, like historical data. These data can either be explicit (ratings given by users to items) or implicit (count data from users listening to songs, clicking on web pages, watching videos, etc).

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.

Build it and they will come. Those were the good ole days. It used to be good enough to design a great app. Add to that an engaging user experience (UX), positive feedback, a high ranking and word of mouth, and your app was ensured continued success. Nowadays however, mobile consumers are simply overwhelmed by choice.

It's been six years since Apple added Siri to iOS and voice became a key way users could interact with technology. In the years since, Google Assistant and Alexa have also established strong footholds as central players in the way we manage myriad services and smart-home devices -- and Cortana has become an integral part of the PC. As much as voice-activated virtual assistants have begun to transform the consumer landscape on devices from smartphones and smartwatches to smart speakers, they have yet to truly break through in the enterprise. That isn't to say we don't already accomplish business tasks using these virtual assistants. Many of us rely on them for quick tasks such as getting directions, scheduling appointments and responding to messages.

Alexa's smart home skills aren't just for turning on the lights or locking your door these days -- now, they can help fulfill your culinary ambitions. Amazon has added cooking abilities to its Smart Home Skill framework, letting you control microwaves (and eventually conventional ovens) with your voice. Instead of pressing umpteen buttons, you can simply ask Alexa to "defrost 3lbs of chicken." Suffice it to say this could be helpful if you don't want to start cooking right away, or if you just hate your microwave's interface. Expect to see the cooking features in use very soon.

Microsoft unveiled its Cortana-powered thermostat, called GLAS, back in July, and now we have more details on it. The software giant partnered with Johnson Controls, the maker of the first in-room thermostat, to create the device, and it's a beauty. It also comes with a hefty price tag: $319, and is available for pre-order now for delivery in March 2018. GLAD is powered by a Windows 10 IoT Core and features a gorgeous translucent touch display. You can control the temperature, check the weather, monitor both indoor and outdoor air quality and more.

A.O. Scott is a film critic at the New York Times. He sits down with Isaac Chotiner to discuss the year in movies, being a film critic in the age of Rotten Tomatoes, and wrestling with Hollywood in a post–Harvey Weinstein world.

Microsoft didn't have much luck in the digital music realm, from the Zune to its Groove Music service. At the end of 2017, the company switched all of its existing Groove users over to Spotify and shut Groove down. But now it turns out the move came with an unforeseen complication, as reported by Neowin. Cortana, Microsoft's smart assistant, can no longer recognize individual songs. Previously, users could use the song identification feature by pressing Cortana's music icon while a song was playing.

Robotics is already changing how we live, shop, invest, travel, and soon, robo-caregivers will transform how we provide care. Advances in AI will deliver extraordinarily innovative services in support of our loved ones. However, the use of robots to care for our children, elderly and disabled will also give rise to some very human questions. Caregiving is social science jargon for providing unpaid support to a family member or friend who has physical, psychological or development needs. Most caregivers do not know what a caregiver is or even know that they are caregivers.