DeepMind acquired startup by Google for 500M established a new collaboration with University of Oxford. The news is announced by Demis Hassabis, co-founder of DeepMind and VP of engineering at Google from a blog-post [1]. Deep learning researchers Prof Nando de Freitas, Prof Phil Blunsom, Dr Edward Grefenstette and Dr Karl Moritz Hermann, from University of Oxford, who teamed up earlier this year to co-found Dark Blue Labs, are hired by DeepMind. Also Dr Karen Simonyan, Max Jaderberg and Prof Andrew Zisserman, one of the world's foremost experts on computer vision systems, and they recently have a start-up called Vision Factory will join DeepMind from University of Oxford[1,2]. The three professors hired by DeepMind are holding joint appointments at Oxford University where they will continue to spend part of their time.

Thanks to a new deep learning system from Yahoo! Research, GIFs are just one more art form--in addition to poetry and calligraphy, to name a few--that computers are quickly mastering. A computer made that all on its own. In fact, not only did a computer make the above GIF, it actually scanned the original video and decided which bits had the highest GIF potential; a video went in, and a slew of appealing GIFs came out. We're on our way to what you could call a fully automated, bean-to-bar, GIF-making solution. Research in New York do, you could call it Video2GIF.

College of Computing Professor Ashok Goel teaches Knowledge Based Artificial Intelligence (KBAI) every semester. And every time he offers it, Goel estimates, his 300 or so students post roughly 10,000 messages in the online forums -- far too many inquiries for him and his eight teaching assistants (TA) to handle. That's why Goel added a ninth TA this semester. Her name is Jill Watson, and she's unlike any other TA in the world. Jill is a computer -- a virtual TA -- implemented, in part, using technologies from IBM's Watson platform.

Google has built its own computer chip. And this won't be the last. The Internet's most powerful company sent a few shock waves through the tech world yesterday when it revealed that a new custom-designed chip helps run what is surely the future of its vast online empire: artificial intelligence. In building its own chip, Google has taken yet another step along a path that has already remade the tech industry in enormous ways. Over the past decade, the company has designed all sorts of new hardware for the massive data centers that underpin its myriad online services, including computer servers, networking gear, and more. As it created services of unprecedented scope and size, it needed a more efficient breed of hardware to run these services.

What is driving this is that we have passed a tipping point a few years back with the convergence of faster cheap computing power and faster broadband and local wifi network speeds to enable better near instant search and complex response. These means the old world of click and search and bad voice recognition or at best clunky responses has moved on into smooth rapid better voice, face, gesture, and text recognition now in real time. Why this is fundamentally important is that it means we will increasingly not touch a keyboard or smartphone or tablet screen but use our voice to do the same thing but more importantly, it will also "talk back" and recommend and assist with personalized services or connected room or car situational advice. Thirdly, it also means that the earlier attempts of virtual reality with Google Glass and Microsoft Kinect have shifted from fad and game inside a closed virtual environments to a bigger open assisted augmented reality of connected things.

As ecommerce evolves into delivery models with real-time fulfillment and digital downloads, the response time to respond to fraud attacks is shrinking fast. Fraud attacks are more sophisticated – as technology evolves fraudsters have elevated their game on payment fraud.

This is the fourth article of the "Big Data Processing with Apache Spark" series. Please see also: Part 1: Introduction, Part 2: Spark SQL and Part 3: Spark Streaming. Machine learning, predictive analytics, and data science topics are getting a lot of attention in recent years for solving real world problems in different business domains in several organizations. Spark MLlib, Spark's Machine Learning library, includes several different machine learning algorithms for Collaborative Filtering, Clustering, Classification and other machine learning tasks. In the previous articles in "Big Data Processing with Apache Spark" series, we have looked at what Apache Spark framework is (Part 1), how to leverage the SQL interface to access data using Spark SQL library (Part 2) and real-time data processing & analytics of streaming data using Spark Streaming (Part 3). Compose makes it simple to deploy production-ready databases in minutes in the cloud or on your own servers. In this article, we'll discuss machine learning concepts and how to use Apache Spark MLlib library for running predictive analytics.

As explained in the I/O keynote, Allo is designed to learn over time, making conversations easier and more productive. Allo makes your phone into the ultimate smartphone. Allo's features include emojis and stickers, gesture controls, the option to send full-bleed photos and doodle on them (much like Snapchat), an incognito mode to ensure private messages, and Smart Reply. The Smart Reply features works closely with Google Assistant and makes the most out of the machine learning capability of the app. If you type that you're craving pizza, Smart Reply will automatically pull up options for deliveries from nearby restaurants.

WIRE)--TSYS (NYSE: TSS), today announced an agreement with Featurespace, a global leader in adaptive behavioral analytics, that will reduce fraud for its clients with a revolutionary machine learning software platform -- the ARICSM engine -- that monitors every individual -- one customer at a time -- to deliver real-time decision capabilities. "We are proud to be working with TSYS to deliver world-leading machine learning fraud protection and exceptional customer management to their clients." Featurespace is the world-leader in Adaptive Behavioural Analytics and creator of the ARICSM engine, a machine learning software platform which understands individual behaviours in real-time for decision making around fraud, risk and compliance. We provide the ARIC Fraud Hub to organisations in banking, payments, and gaming to spot new fraud attacks as they occur, reduce customer friction by reducing false fraud alerts, and improve operational efficiencies in managing fraud, risk and compliance.

In a previous post I wrote about how to build a'People Who Like This Also Like ...' feature for displaying lists of similar musicians. My goal was to show how simple Information Retrieval techniques can do a good job calculating lists of related artists. For instance, using BM25 distance on The Beatles shows the most similar artists being John Lennon and Paul McCartney. One interesting technique I didn't cover was using Matrix Factorization methods to reduce the dimensionality of the data before calculating the related artists. This kind of analysis can generate matches that are impossible to find with the techniques in my original post.