Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generation tasks: a temporally-directed unsupervised video prediction task to learn richer context-aware video encoder representations, and a logically-directed language entailment generation task to learn better video-entailed caption decoder representations. For this, we present a many-to-many multi-task learning model that shares parameters across the encoders and decoders of the three tasks. We achieve significant improvements and the new state-of-the-art on several standard video captioning datasets using diverse automatic and human evaluations. We also show mutual multi-task improvements on the entailment generation task.

A small collection of introductory scikit-learn and Python stack tutorials for those with an existing understanding of machine learning looking to jump right into using a new set of tools.

Under the wrong conditions, 'stop' could mean'go faster' to an autonomous car. A new study led by the University of Washington found that the type of computer brain set to be used in autonomous cars could be fooled into thinking a Stop sign is a 45 mph Speed Limit or other sign by adding just a little graffiti. The researchers peppered one Stop sign with a few black and white blocks, and used stickers to make another read "Love Stops Hate." In both cases, the deep neural network processing images fed to it by a camera misread the signs most of the time, even though they retained their octagonal shape and red background color. Another test simulated a slightly faded right turn arrow, which the computer often thought was a Stop sign or added lane sign, but which a human would have no trouble identifying.

You are free to share this article under the Attribution 4.0 International license. A new method uses artificial intelligence to accurately detect brain damage caused by concussions years after the trauma happened. "With 1.6 to 3.8 million concussions per year in the US alone, the prevalence of this injury is alarming…" While the short-term effects of head trauma can be devastating, the long-term effects can be equally hard for patients. The symptoms may linger years after the concussion happened. The problem is it is often hard to say whether their symptoms are being caused by a concussion or other factors like another neurological condition or the normal aging process.

At The Seeing Eye guide dog facility in Morristown, New Jersey, puppies spend the first three weeks of their life in plastic kiddie pools--the blue kind, speckled with colorful undersea cartoons. Lined with fleece and towels, the wading pools are perfectly sized for a litter of soft, tiny puppies and their mama to lounge and nurse. And some of those floppy-eared, tiny-tailed puppies will eventually grow into responsible, diligent, working dogs. But to don that Seeing Eye guide dog vest, a dog needs to be exceptional. Guide dogs need to be healthy, unfazed by jackhammers, and smart enough to lead a human across the street only when the coast is clear.

Recent studies show that customer satisfaction with Swedish banks is at a 20 year low. Customers don't trust banks, in fact Sweden has recently turned to AI to help improve customer satisfaction -- and I have to admit when I read that, I had to read it twice. You're implementing more technology to improve customer satisfaction? Usually when banks want to stop frustrating customers they make it easier to opt out of self-help technology and talk to a person. Enter chatbots such as Nina, a new release from Swedbank.

Researchers at the University of East Anglia, Caltech, Carnegie Mellon University and Disney have created a way to animate speech in real-time. With their method, rather than having skilled animators manually match an animated character's mouth to recorded speech, new dialogue can be incorporated automatically in much less time with a lot less effort. To do this, the researchers recorded over eight hours of audio and video of a speaker reciting more than 2500 different sentences. The speaker's face was tracked as they spoke, which was used to create a reference face for an animation model. Off-the-shelf speech recognition software was then used to transcribe the speech sounds.

Here is a list of the best courses in Data Science and Machine Learning from Udemy. With the back-to-school sale, you can get these and other Udemy courses for $12 ($10 if it is your first purchase), 90-95% off original price. Offer expires on Aug 10, 2017. Udemy.com is an online marketplace for learning, their data science content is updated regularly by the instructors who created good courses (filled with actionable tools) and bite-size lessons that help you cover defined topics at your own pace. Ready to be thrown into the deep end and learn the real problems a data scientist faces on a daily basis?

With organizations like the Partnership on AI, we're already starting to see signs that companies recognize and want to address the dangers of an AI race. But for now, the Partnership is comprised mainly of western organizations, while companies in many countries and especially China are vying to catch up to ― and perhaps "beat" ― companies in the U.S. and Europe. How can we encourage organizations and research teams worldwide to cooperate and develop safety standards together? How can we help teams to monitor their work and ensure proper safety procedures are always in place? AI research teams will need the feedback and insight of other teams to ensure that they don't overlook potential risks, but how will this collaboration work without forcing companies to reveal trade secrets? What do you think of the Race Avoidance Principle?

A quick, hassle-free way to stay on top of robotics news, our robotics digest is released on the first Monday of every month. Sign up to get it in your inbox. From wacky talking Einsteins to clumsy security'bots, from speedy drones to the underwater operations at Fukushima, it's been another busy month. So let's kick off our July review with a look at robots in action! You'd be forgiven for missing this first one.