In the existing literature of deep learning, is there any work that deals with capturing uncertainty like Bayesian models do?

Many spectral unmixing methods rely on the non-negative decomposition of spectral data onto a dictionary of spectral templates. In particular, state-of-the-art music transcription systems decompose the spectrogram of the input signal onto a dictionary of representative note spectra. The typical measures of fit used to quantify the adequacy of the decomposition compare the data and template entries frequency-wise. As such, small displacements of energy from a frequency bin to another as well as variations of timber can disproportionally harm the fit. We address these issues by means of optimal transportation and propose a new measure of fit that treats the frequency distributions of energy holistically as opposed to frequency-wise. Building on the harmonic nature of sound, the new measure is invariant to shifts of energy to harmonically-related frequencies, as well as to small and local displacements of energy. Equipped with this new measure of fit, the dictionary of note templates can be considerably simplified to a set of Dirac vectors located at the target fundamental frequencies (musical pitch values). This in turns gives ground to a very fast and simple decomposition algorithm that achieves state-of-the-art performance on real musical data.

You might not be campaigning to be America's next president, or have any desire to hold such a demanding office (bless you, Hillary), but wouldn't it still be nice to be treated like POTUS when you travel? Or, at least spend a few days in the presidential suite feeling like one of the world's most … Election jokes are i Saturday Night Live' /i s bread and butter, so it should come as no surprise that the cast took aim at Donald Trump's hot mic scandal. But host Lin-Manuel Miranda also got a chance to shine in his opening monologue. Below, we've rounded up the must-see moments from last night's /b … Humans may live longer and longer, but eventually we all grow old and die. This leads to a simple question: Is there an intrinsic maximum limit to human lifespan or not?

At last year's Spark Summit conference, Patrick Wendell, a software engineer at Databricks Inc. and a contributor to the Apache Spark open source project, said the technology's data processing capabilities are impressive but its real power lies in the Spark library components that sit on top of the core engine. "The future of Spark is the libraries," he said. "That's what the community has invested in and where the innovation is coming from." Sure enough, this month's Spark Summit 2015 event prominently featured case studies in which users explained how they're putting the libraries to work in Spark analytics applications. The Spark platform comes with four distinct libraries -- Spark SQL, Spark Streaming, a graph processing library called GraphX and a machine learning one known as MLlib -- that include pre-built algorithms and programming capabilities designed to streamline data preparation, exploration and analysis tasks. The libraries enable users to automate certain tasks and eliminate some of the coding that typically would be required.

No technology trend today comes with more hype than artificial intelligence. Yet AI researchers often joke that most people don't quite see how it's changing the world--because as soon as something like Siri or Nest weaves itself into our lives, people forget it's "artificial." That sort of quiet takeover of AI has already begun in an industry we humans tend to hold pretty sacred--news. Last year, Associated Press announced that the majority of its earnings reports will eventually be written with AI-enabled software. While the company argues it will free up reporters to do more analytical work, the question it raises is unsettling: Should we just leave it to the machines to interpret what they see in piles of Big Data and write up the results?

Applications that use some sort of AI are a dime a dozen. Artificial intelligence is now running robots, speech-to-text programs, cars, and doing everything from creating movie trailers to composing music. Google wants to take that to a whole new level. The search giant has announced its newest product this weekend: the Google Assistant, a voice-activated digital helper powered by AI. Now, Google doesn't normally build its own smartphones or gadgets, but they did for Assistant. On their own, these devices have merit but don't really stand out next to Amazon's Echo or Apple's iPhone 7. What makes them interesting is Assistant, which is controlled through simple voice commands and offers a more conversational style than Apple's Siri.

Samsung acquires Viv, a next-gen AI assistant built by the creators of Appleâ s Siri (techcrunch.com) Has anybody heard when they plan to release Viv to the public?

Apple chief executive Tim Cook is among the leading industry experts touting artificial intelligence as a tech on the cusp of world domination. Talking about the evolution of the smartphone, Cook told the Washington Post: "AI will make this product even more essential to you. It will become even a better assistant […] where you probably aren't leaving home without it today – you're really going to be connected to it in the future." But how so – will we soon be permanently wired to the web? Not quite, but we will have something that is, and is set to be very smart indeed.

Humans may live longer and longer, but eventually we all grow old and die. This leads to a simple question: Is there an intrinsic maximum limit to human lifespan or not? There are two equally simple answers. Either there is a limit or there isn't. Soft pretzels are one of the best things to come out of concession stands, but homemade pretzels are a million times better.

Artificial intelligence has been a trope of science fiction for decades. From the unsettling and double-crossing HAL in the film 2001: A Space Odyssey to the oppressive robots enslaving humanity in The Matrix and The Terminator, the concept of sentient machines outsmarting and overthrowing their creators has long permeated popular culture. If these movies are anything to go by, credit risk managers should be worried. Machine learning, a subset of AI that allows computers to answer simple questions...