Microsoft has broadened open-source access to its Computational Network Toolkit, in a move that underscores the ongoing arms race around machine learning technology. CNTK had initially been made available on Microsoft's Codeplex site in April 2015 through under an academic license, but now it has been... To read the full story, Sign In to your Research Unlimited or Executive Network account, or Subscribe. Constellation Research, Constellation SuperNova Awards, Connected Enterprise, and the Constellation Research logo are trademarks of Constellation Research, Inc. All other products and services listed herein are trademarks of their respective companies.

The efficient stock market hypotheses (EMH) has been the subject of much controversy and research since its publication. The EMH is an investment theory that asserts that it is impossible to out perform market returns. According to the hypothesis, it is not possible because of stock market efficiency. Stock market efficiency causes share prices to incorporate and reflect all pertinent market information. By the nature of this assertion it makes it impossible for the stock to be either over or undervalued.

Those of you subscribing to the nupic-theory mailing list are aware that a new research paper describing a mathematical model for the spatial pooler (SP) has emerged. Many of us have asked "What is the math behind the SP?" or "How can I use the SP for machine learning". The goal of this paper is to address those very questions, bridging the gap between HTM and the machine learning community. This work is part of a much larger body of work being conducted by the Rochester Institute of Technology's (RIT's) NanoComputing Research Lab. Our lab is specifically focused on designing energy efficient hardware circuits and architectures that are biologically inspired.

SOMETIMES it is perceived as a figment of the far future. But artificial intelligence (AI) is today's great obsession in Silicon Valley. Last year technology companies spent 8.5 billion on deals and investments in artificial intelligence, four times more than in 2010. Nearly all of the world's technology giants, including Google, Microsoft, Facebook, Amazon and Baidu, are competing fiercely to hire the best AI experts, snap up start-ups and pour money into research. The technology has not always been so popular.

LIVERMORE, Calif. and ARMONK, N.Y. - 29 Mar 2016: Lawrence Livermore National Laboratory (LLNL) today announced it has purchased a first-of-a-kind brain-inspired supercomputing platform for deep learning inference developed by IBM (NYSE: IBM) Research. Based on a breakthrough neurosynaptic computer chip called IBM TrueNorth, the scalable platform will process the equivalent of 16 million neurons and 4 billion synapses and consume the energy equivalent of a tablet computer – a mere 2.5 watts of power for the 16 TrueNorth chips. The brain-like, neural network design of the IBM Neuromorphic System is able to infer complex cognitive tasks such as pattern recognition and integrated sensory processing far more efficiently than conventional chips. "Neuromorphic computing opens very exciting new possibilities and is consistent with what we see as the future of the high performance computing and simulation at the heart of our national security missions," said Jim Brase, LLNL deputy associate director for Data Science. "The potential capabilities neuromorphic computing represents and the machine intelligence that these will enable will change how we do science."

This is an introductory tutorial on using Theano, the Python library. I'm going to start from scratch and assume no previous knowledge of Theano. However, understanding how neural networks work will be useful when getting to the code examples towards the end. I recently gave this tutorial as a talk in University of Cambridge and it turned out to be way more popular than expected. In order to give more people access to the material, I'm now writing it up as a blog post. I do not claim to know everything about Theano, and I constantly learn new things myself.

Some of today's top techies and scientists are very publicly expressing their concerns over apocalyptic scenarios that are likely to arise as a result of machines with motives. Among the fearful are intellectual heavyweights like Stephen Hawking, Elon Musk, and Bill Gates, who all believe that advances in the field of machine learning will soon yield self-aware A.I.s that seek to destroy us--or perhaps just dispose of us, much like scum getting obliterated by a windshield wiper. In fact, Dr. Hawking told the BBC, "The development of full artificial intelligence could spell the end of the human race." Indeed, there is little doubt that future A.I. will be capable of doing significant damage. For example, it is conceivable that robots could be programmed to function as tremendously dangerous autonomous weapons unlike any seen before.

The working relationship between people and technology is fundamentally shifting. Employees used to learn the language of business applications to use them. A world where Shift F9 created a new line item entry in their expenses. Since then, advances in user experience design have masked the language of technology with buttons and guided navigation. The user training toll has decreased but it has by no means gone away.

Andrej Karpathy knows what it's like to compete with artificial intelligence. He first went head-to-head with an artificial intelligence algorithm in 2011. A team of Stanford University researchers had just built the world's most effective image-recognition software, and he wanted to see how well his very real brain stacked up against their digital creation on what was, at the time, a standard image recognition test. The Stanford software analyzed a pool of about 50,000 images, slotting each into one of 10 categories, such as "dogs," "horses," and "trucks." It was right about 80 percent of the time.

The impressive machine dispatched the reigning (living and breathing) Go champion 4-1 in the best-of-5 series. The Go board game, which originated in China, requires complex strategic thinking with the number of possible outcomes dwarfing that in chess. AlphaGo's win demonstrates the emergence of intuition with the abstract strategic thinking not mastered in previous artificial intelligence ventures. AlphaGo's systems include'deep learning' methods, allowing the machine to run thousands of simulated scenarios to build its "experiences" to use when playing the game for real. The use of neural networks allows problem-solving without any prior programming.