The extension of image generation to video generation turns out to be a very difficult task, since the temporal dimension of videos introduces an extra challenge during the generation process. Besides, due to the limitation of memory and training stability, the generation becomes increasingly challenging with the increase of the resolution/duration of videos. In this work, we exploit the idea of progressive growing of Generative Adversarial Networks (GANs) for higher resolution video generation. In particular, we begin to produce video samples of low-resolution and short-duration, and then progressively increase both resolution and duration alone (or jointly) by adding new spatiotemporal convolutional layers to the current networks. Starting from the learning on a very raw-level spatial appearance and temporal movement of the video distribution, the proposed progressive method learns spatiotemporal information incrementally to generate higher resolution videos. Furthermore, we introduce a sliced version of Wasserstein GAN (SWGAN) loss to improve the distribution learning on the video data of high-dimension and mixed-spatiotemporal distribution. SWGAN loss replaces the distance between joint distributions by that of one-dimensional marginal distributions, making the loss easier to compute. We evaluate the proposed model on our collected face video dataset of 10,900 videos to generate photorealistic face videos of 256x256x32 resolution. In addition, our model also reaches a record inception score of 14.57 in unsupervised action recognition dataset UCF-101.

Technology has shaped the way on which we compose and produce music: Notably, the invention of microphones, magnetic tapes, amplifiers and computers pushed the development of new music styles in the 20th century. In fact, several artistic domains have been benefiting from such technology developments; for instance, Experimental music, nonlinear music, Electroacoustic music, and interactive music. Experimental music is composed in such a way that its outcome is often unforeseeable; for instance, it may contain random generated tones, computer-generated content, variable-duration notes and "free" content. It may also include atonal melodies and microtones. Another domain is nonlinear music, in which the scenario is divided in parts whose order can be chosen at execution time. We will use the term "nonlinear" music in that sense. Nonlinear music exists from many centuries ago; for instance, Mozart's minuets in which the order of work's musical material was determined by coin-tosses. Electroacoustic music was originated by the incorporation of electronic sound production into compositional practice.

Last December, the world ushered in a new era of popular music: human and artificial intelligence (AI) collaboration. Musical eras are often defined by their dominant modes of production -- analog, electronic, digital -- each bringing about new styles and ways of listening. This era is marked by the release of the first AI-human collaborated album, Hello World, by the music collaborative Skygge. Skygge, led by composer and producer Benoît Carré and musician and tech researcher François Pachet, translates to "shadow" in Danish and was inspired by the Hans Christian Andersen story of the same name. We now know that algorithms can learn human bias, but can they also create highly creative and emotionally engaging music?

I think it is a really exciting realm of Computer Science and may turn out to be the most important advancement that I've seen in my career. More exciting, impactful and innovative than virtualization, cloud computing or IoT! I've been studying it in my free time. Consider this blog post an initial primer on the topic. What does ML & AI really mean? Machine Learning and Artificial Intelligence are being used interchangeably in the industry today, but they really mean different things and can hence cause confusion. Artificial intelligence is a broad term that has been used for many years and refers to machines being able to carry out tasks that mimic using human intelligence.

Yury leads a team comprising UX and visual designers at one of the largest Russian Internet companies, Mail.Ru Group. Upgrade your inbox and get our editors' picks twice a month. Digital products are getting more and more complex. In this article, Yury Vetrov explains why we need to support more platforms, tweak usage scenarios for more user segments, and hypothesize more. I've been following the idea of algorithm-driven design for several years now and have collected some practical examples. The tools of the approach can help us to construct a UI, prepare assets and content, and personalize the user experience. The information, though, has always been scarce and hasn't been systematic. However, in 2016, the technological foundations of these tools became easily accessible, and the design community got interested in algorithms, neural networks and artificial intelligence (AI). Now is the time to rethink the modern role of the designer.

While artificial intelligence researcher Yves Bergquist believes we're "far away" from AI being able to take over for screenwriters, he said Tuesday at The Grill 2018 that could still have tremendous impact on the kinds of stories that get made in Hollywood. That's in part due to how AI applications could help process "low level data" for studios that could help them think beyond their assumptions about what audiences will or will not embrace. Also Read: Why eSports Is'Growing Like Wildfire,' From Activision Blizzard to Echo Fox "If you look at the mathematical structure of narrative that's been told in film or TV, you see there are not that many unique stories," he said at the event, held at the SLS Hotel Beverly Hills. "I think what's going on is creators are censoring themselves and telling the stories that are tried and true over and over and over again." "My hunch is that there are many, many, many more stories that are possible, desirable, that can be told," he added.

The CEO of a Cambridge-based Artificial Intelligence startup is helping to fashion pan-European governance and regulation of the rocketing technology segment. Dr Loubna Bouarfa of OKRA Technologies is one of 52 thought leaders on the advisory brains trust – the EU High-Level Expert Group on AI – and spent a week at a Brussels summit. Discussions were held in the European Parliament covering topics from programming bias, data security, error accountability and responsible workflows. As the founder and CEO of OKRA, a St John's Innovation Centre company, Dr Bouarfa represents AI practitioners and the healthcare space in particular. She said: "It is an honour to represent the innovative AI startup ecosystem, balancing an operational mindset with my ethical convictions. In my work at OKRA and beyond, ethical considerations around responsibility, transparency and accountability are always top of mind."

NEW YORK (FOX5NY.COM) - A singer and YouTube creator is making music history. Taryn Southern's video for the song "Break Free" has racked up more than 2 million views. She used artificial intelligence software to co-write and co-produce the song, which features passionate vocals and a pulsating beat. So why stop at one song? So Taryn just released what is said to be the first album co-written and co-produced by artificial intelligence.

It's software, let's be clear on that, it's just an application. Sorry to disappoint you but it's not a physical network of brains floating in slimy green liquid, or an army of cognitively connected robots, it's just an application. In fact, it's often just part of another application, such as Snapchat. A neural network is just a particular type of application that is very good at taking a bunch of data and giving you an answer to a question. One of the most commonly used examples is of course identifying photos with cats in them.

BootstrapLabs, a leading venture capital firm focusing on Applied AI and based in Silicon Valley, announced today the 4th annual Applied Artificial Intelligence Conference will be held in San Francisco on April 18, 2019. The BootstrapLabs Applied Artificial Intelligence Conference (#AAI19) has grown to become one of the top AI events in the U.S. Mentioned in publications such as Forbes, TechCrunch and Fortune, and selected by Business Insider as one of the top 20 AI conferences to attend, the exclusive conference has brought together over 2,000 professionals and is considered by many AI leaders to be the best forum to learn, network and discover the latest Applied AI technologies. The one-day conference will focus on the latest and future impacts of AI applications across a breadth of sectors including Transportation, Logistics, Healthcare, Energy, FinTech, the Future of Work, IoT and Cybersecurity. The conference will take place in downtown San Francisco and will feature keynotes from Artificial Intelligence leaders who will share practical wisdom and methodologies on how to take advantage of AI's powerful potential. Many CTOs, CIOs and AI/ML experts from top tech companies like Facebook, Amazon, Uber, MasterCard, Unity, Airbnb, Linkedin, Intel, Samsung, Tesla, JP Morgan, Comcast, Microsoft, IBM, Walmart and many others, including top AI founders and government officials, have been participating during past conference editions.