This will enable more people in your organization to leverage machine learning and most importantly allow domain experts to rapidly prototype ML solutions and validate their hypothesis before involving data scientists. If you are an experienced data scientist, automated ML will let you improve productivity and save time by eliminating the need to manually perform the tedious and repetitive tasks of feature engineering, algorithm selection and hyperparameter tuning. You can even start by generating a model with automated ML as a starting point and tune it further. Organizations can also use automated ML to benchmark their models. Many Fortune 500 customers are benefiting from using automated ML. These include a global oil & refinery enterprise that's using automated ML to forecast reservoir production and a medical devices company that's using automated ML for predictive maintenance. Automated ML also powers Microsoft Power BI's AI capabilities, where business analysts can build machine learning models without writing a single line of code. Azure Machine Learning service's automated ML capability is based on a breakthrough from our Microsoft Research division and different from competing solutions in the market. The approach combines ideas from collaborative filtering and Bayesian optimization to search an enormous space of possible machine learning pipelines intelligently and efficiently.

When I was a kid, I was certain that by the time I was a grown woman, I'd have a friendly little robot friend. Adulthood was in the FUTURE, and the FUTURE had robots like R2-D2, Threepio, Data, and so on. Alas, I am a tax-paying adult with a full-time job, and no, I do not have an adorable mechanical friend that comically beep-boops its disapproval when I get up to my hijinks and shenanigans. But around this time last year, I had an inkling of hope that this future was at least on the horizon. Mayfield Robotics's Kuri Robot was lovable, functional, and buzzworthy with its cute mannerisms and deft behavioral touches. Like, it'd wiggle and waggle as it maneuvered around a room.

Artificial Intelligence – specifically machine learning and deep learning – was everywhere in 2018 and don't expect the hype to die down over the next 12 months. The hype will die eventually of course, and AI will become another consistent thread in the tapestry of our lives, just like the internet, electricity, and combustion did in days of yore. But for at least the next year, and probably longer, expect astonishing breakthroughs as well as continued excitement and hyperbole from commentators. This is because expectations of the changes to business and society which AI promises (or in some cases threatens) to bring about go beyond anything dreamed up during previous technological revolutions. AI points towards a future where machines not only do all of the physical work, as they have done since the industrial revolution but also the "thinking" work – planning, strategizing and making decisions.

Every morning, without fail, I ask my closest smart speaker to play NPR. Clearly, there's much more that a web-connected, voice-controlled speaker could do. And it seems Google has the same idea: the company announced today that it's developing an open audio news standard for the Assistant. When you ask your Google Home (or any other Assistant-powered device) to play the news, it'll automatically generate a playlist of stories based on your interests using the same technology behind the AI on Google News. Hopefully, that should be more useful than just jumping into whatever your favorite station is playing at that moment.

Amazon is launching a new program that will let its customers answer some of the questions Alexa can't answer on its own. It's called Alexa Answers and starting today, the company will begin inviting select customers to field some of the more difficult questions posed to Amazon's assistant. "While Alexa can answer the vast majority of questions customers are asking every day," Bill Barton, Amazon's VP of Alexa Information, wrote in a blog post, "every once in a while, customers throw curve balls at us with various questions like'Where was Barbara Bush buried?' or'Who wrote the score for Lord of the Rings?' or'What's cork made out of?' or'Where do bats go in the winter?'" The company has been testing the Alexa Answers program internally, and in the past month, it has added more than 100,000 responses. Going forward, customers who have been invited to participate will be able to scroll through topic categories on the Alexa Answers website, choose questions they want to answer and submit a response.

Amazon is rolling out a few tweaks to Alexa that will make it easier to find the music you want to hear. By telling Alexa what you like and don't like and by conversing with Amazon's assistant about what you enjoy listening to, Alexa will be able to create more personalized suggestions and playback even when you just say, "Alexa, play music." If you're looking for Alexa to offer some suggestions for playlists that are tailored to you and what you want, the virtual assistant will now be able to talk to you about what you're looking for. When you say something like, "Alexa, help me find a holiday playlist," or "Alexa, help me find dinner music," Alexa will respond with a few questions to help get a better grasp on what genre, tempo or mood you're hoping to incorporate. Alexa will then customize playback based on how you responded and your past listening history.

This post was done in partnership with Wirecutter. When readers choose to buy Wirecutter's independently chosen editorial picks, it may earn affiliate commissions that support its work. Read Wirecutter's continuously updated list of deals here. Down to $75, this is an excellent value for this M.2 SATA Drive if you have a compatible computer. While we've seen the price of this drive, like all storage, continue to fall in recent months, this is still a good opportunity to save on it as it has recently fallen even more.

Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are available for learning. Learning from the logged feedback is however subject to biases caused by only observing feedback on recommendations selected by the previous versions of the recommender. In this work, we present a general recipe of addressing such biases in a production top-K recommender system at Youtube, built with a policy-gradient-based algorithm, i.e. REINFORCE. The contributions of the paper are: (1) scaling REINFORCE to a production recommender system with an action space on the orders of millions; (2) applying off-policy correction to address data biases in learning from logged feedback collected from multiple behavior policies; (3) proposing a novel top-K off-policy correction to account for our policy recommending multiple items at a time; (4) showcasing the value of exploration. We demonstrate the efficacy of our approaches through a series of simulations and multiple live experiments on Youtube.

German astronaut Alexander Gerst talked with the artificially intelligent crew-assistant CIMON during a 90-minute experiment on Nov. 15 aboard the International Space Station (ISS). According to a statement from the manufacturer, Airbus, Gerst, the commander of the current space station crew, woke up CIMON (the Crew Interactive Mobile CompanioN) with the words "Wake up, CIMON." In response, CIMON said, "What can I do for you?" [This Flying Space Droid Wants to Make Friends with Astronauts] During the experiment, CIMON successfully found and recognized Gerst's face, took photos and video, positioned itself autonomously within the Columbus module using its ultrasonic sensors, and issued instructions for Gerst to perform a student-designed experiment with crystals. Weighing about 5 kilograms (11 lbs. on Earth), the 3D-printed robot designed jointly by the German space agency DLR, Airbus and IBM works similarly to Apple's virtual assistant Siri or Amazon's Alexa. "If CIMON is asked a question or addressed, the Watson AI firstly converts this audio signal into text, which is understood, or interpreted, by the AI," explained IBM project lead Matthias Biniok in the statement.

Item recommendation task predicts a personalized ranking over a set of items for each individual user. One paradigm is the rating-based methods that concentrate on explicit feedbacks and hence face the difficulties in collecting them. Meanwhile, the ranking-based methods are presented with rated items and then rank the rated above the unrated. This paradigm takes advantage of widely available implicit feedback. It, however, usually ignores a kind of important information: item reviews. Item reviews not only justify the preferences of users, but also help alleviate the cold-start problem that fails the collaborative filtering. In this paper, we propose two novel and simple models to integrate item reviews into Bayesian personalized ranking. In each model, we make use of text features extracted from item reviews using word embeddings. On top of text features we uncover the review dimensions that explain the variation in users' feedback and these review factors represent a prior preference of users. Experiments on six real-world data sets show the benefits of leveraging item reviews on ranking prediction. We also conduct analyses to understand the proposed models.