Multi-label classification has received considerable interest in recent years. Multi-label classifiers have to address many problems including: handling large-scale datasets with many instances and a large set of labels, compensating missing label assignments in the training set, considering correlations between labels, as well as exploiting unlabeled data to improve prediction performance. To tackle datasets with a large set of labels, embedding-based methods have been proposed which seek to represent the label assignments in a low-dimensional space. Many state-of-the-art embedding-based methods use a linear dimensionality reduction to represent the label assignments in a low-dimensional space. However, by doing so, these methods actually neglect the tail labels - labels that are infrequently assigned to instances. We propose an embedding-based method that non-linearly embeds the label vectors using an stochastic approach, thereby predicting the tail labels more accurately. Moreover, the proposed method have excellent mechanisms for handling missing labels, dealing with large-scale datasets, as well as exploiting unlabeled data. With the best of our knowledge, our proposed method is the first multi-label classifier that simultaneously addresses all of the mentioned challenges. Experiments on real-world datasets show that our method outperforms stateof-the-art multi-label classifiers by a large margin, in terms of prediction performance, as well as training time.

Video Friday is your weekly selection of awesome robotics videos, collected by your multilayer Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next two months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Also I want that thing that will fire birdies at me. The first robot to autonomously and intentionally break Asimov's first law, which states: A robot may not injure a human being or, through inaction, allow a human being to come to harm.

A 25-year-old Erik Spoelstra used to sit in a storage room in the old Miami Arena, evaluating hours of game film to review player performance as an entry-level NBA video coordinator. Eventually, he climbed out of the audio visual muck to become head coach of the NBA's Miami Heat, where he would go on to win two championships. It's a classic story of rags to riches--rising from junior video coordinator to head coach in about 13 years--and it may now be unlikely to ever happen again, as computers take over the position that gave Spoelstra his start. "If an AI were fed videos of a huge number of past NBA games, and were smart enough to understand the events occurring in the games, then it could do a better job at making tactical basketball decisions like choosing starting lineups," said Ben Goertzel, a prominent futurist and lead researcher in the OpenCog AI lab at Hong Kong's Polytechnic University. "As AIs with robust video understanding become widespread, I'd expect that we could see AI sports assistants start to play a serious role," he said.

Kaname Hayashi is known as the "Father of Pepper." Hayashi is the "father of Pepper," the charming humanoid robot from Japanese carrier SoftBank Mobile and French company Aldebaran Robotics. Pepper, with its circular doe eyes and welcoming smile, is billed as a robot that can read your emotions. It's available for sale and has even enrolled in school. Like any proud parent whose kids leave home, Hayashi had a void to fill.

Anirudh Koul's grandfather was slowly losing his ability to see. By 2014, he was having a hard time recognizing Koul's face in their weekly Skype calls bridging the vast distance between the Silicon Valley, where Koul is a data scientist at Microsoft, and the elderly man's home in New Delhi. So Koul started reading up on the challenges of vision loss and thinking about how the recent advances in deep learning, a potential-packed area of machine learning, could help give people a new way to recognize what's around them without actually seeing it. That was the modest beginning of Seeing AI. Two years later, Microsoft CEO Satya Nadella introduced the budding technology to thundering applause at this year's Build conference.

ZUMATA, a Singapore-based hotel distribution and technology company, along with DHISCO, the world's leading hospitality distribution company headquartered in Dallas, Texas, today announced a reciprocal agreement aimed to increase each other's hotel inventory while accelerating their mutual geographic expansion of distribution. ZUMATA, through its extensive network of wholesale partners and channel managers will supplement DHISCO's inventory by providing over 500,000 instantly bookable hotel properties. For ZUMATA, DHISCO will facilitate distribution of this hotel inventory to its large customer base largely based in North America and other Western markets. "DHISCO has been an industry powerhouse for years, and yet their management is keenly focused on innovation," said ZUMATA CEO Josh Ziegler. "This partnership underscores their commitment to staying at ahead of their competition by embracing the latest technological advancements. For us, this partnership represents a significant opportunity for our partners to gain access to DHISCO's amazing distribution. Complementing inventory and distribution, our artificial intelligence, or AI, powered technology will add exciting new capabilities that can increase customer satisfaction while increasing performance and conversions for all of us."

The edtech trend on the tip of everyone's tongue at this year's EdtechXEurope event is artificial intelligence. By harnessing the power of AI and deep learning, educators can glean insights from the vast quantities of data hoovered up from their students. AI could also help lecturers make better decisions and could improve student retention rates, according to experts. "AI is a tool to make better sense of data," says Satya Nitta, director of education and cognitive sciences at IBM. The world's top online learning platforms are working with business schools such as Yale SOM and Duke Fuqua, and are offering advanced analytical tools to help them refine and enhance student learning.

Lydia Ainouz draws a small crowd to watch her playing the Yakuza video game during the opening day of the Electronic Entertainment Expo. The Electronic Entertainment Expo wrapped Thursday, giving retailers, distributors and video game fans a taste of what interactive fun is arriving this year and beyond. Women are playing more key roles in video games beyond just serving as damsels in distress, or worse, as discarded victims. And game makers are including a few more lead characters who aren't white. More women took the biggest stages at E3, including Electronic Arts' Jade Raymond, whose EA Motive Studio is working on a series of Star Wars games, and Microsoft's Shannon Loftis, the head of Microsoft Studios Publishing.

Here is a situation that I found myself in, and I'm sure other smart-home users can relate to it. A couple of weeks ago, while on a business trip in China, my smart doorbell (such as ring) rang. I picked up my smartphone to see who was at the door. To my surprise, it was my daughter standing outside our house. Although it was daytime in my location, she was standing in the dark, back at home.

Elon Musk has released video footage of SpaceX's latest landing attempt, in which the aerospace firm lost a Falcon 9 rocket. The Falcon 9 took off from Cape Canaveral in Florida on Wednesday, carrying two communications satellites into orbit. Looks like early liquid oxygen depletion caused engine shutdown just above the deck pic.twitter.com/Sa6uCkpknY Head of SpaceX, Elon Musk, has released video footage showing just how close the first stage of this week's rocket launch came to successfully landing on the floating barge. The Falcon 9 appeared to be on course for an upright landing before it was lost in clouds of smoke.