One difficulty faced by artificial intelligence is predicting what humans are going to do next. To help solve that problem, researched have trained an algorithm by making it binge-watch TV. Computer vision experts from MIT's Computer Science and Artificial Intelligence Lab (CSAIL) made an algorithm watch 600 hours of TV shows including Ugly Betty, Scrubs, The Big Bang Theory, The Office (US) and more. In each of the clips, taken from YouTube, humans were performing tasks and interacting with each other. After analysing the videos, the AI was then made to watch a clip it hadn't seen before and predict what would happen.

The ability to make continual, accurate decisions based on evolving data is key in many of today's data-driven intelligent systems. This tutorial-style talk presents an introduction to the modern study of sequential learning and decision making under uncertainty. The broad objective is to cover modeling frameworks for online prediction and learning, explore algorithms for decision making, and gain an understanding of their performance. Specifically, we will look at multi-armed bandits- models of decision making that capture the explore-vs-exploit tradeoff in learning, regret minimization, non-stochastic or adversarial online learning, and online convex optimization. Time permitting, we will discuss new directions and frontiers in the area of sequential decision making.

In machine learning often a tradeoff must be made between accuracy and intelligibility: the most accurate models usually are not very intelligible (e.g., random forests, boosted trees, and neural nets), and the most intelligible models usually are less accurate (e.g., linear or logistic regression). This tradeoff often limits the accuracy of models that can be applied in mission-critical applications such as healthcare where being able to understand, validate, edit, and trust a learned model is important. We have developed a learning method based on generalized additive models (GAMs) that is often as accurate as full complexity models, but remains as intelligible as linear/logistic regression models. In the talk I'll present two case studies where these high-performance generalized additive models (GA2Ms) are applied to healthcare problems yielding intelligible models with state-of-the-art accuracy. In the pneumonia risk prediction case study, the intelligible model uncovers surprising patterns in the data that previously had prevented complex learned models from going to clinical trial, but because it is intelligible and modular allows these patterns to easily be recognized and removed.

The state-of-the-art in object recognition has undergone dramatic changes in the last 20 years. In this talk, I will review the progression of the field and discuss why various approaches both succeeded and failed. The talk will cover visual recognition from the early 90's, including handwritten digit and face detection, to the current state-of-the-art in deep learning applied to object categorization. Algorithms will be explained at an intuitive level. The talk is aimed at the non-expert in computer vision with some knowledge of machine learning.

Last month NVIDIA, our favorite GPU vendor, dived into the converged appliance space. In fact we might call their new NVIDIA DGX-1 a hyperconverged supercomputer in a 4U box. Designed to support the application of GPU's to Deep Learning (i.e. The price is surprisingly affordable, and can replace the 250 server cluster you might otherwise need for effective Deep Learning. Despite the obvious opportunities, enterprises face a lot of obstacles in putting machine learning (and esp.

Versu is a text-based simulationist interactive drama. Because it uses autonomous agents, the drama is highly replayable: you can play the same story from multiple perspectives, or assign different characters to the various roles. The architecture relies on the notion of a social practice to achieve coordination between the independent autonomous agents. A social practice describes a recurring social situation, and is a successor to the Schankian script. Social practices are implemented as reactive joint plans, providing affordances to the agents who participate in them.

Facebook is well known for its early and increasing use of artificial intelligence. The social media site uses AI to pinpoint its billion-plus users' individual interests and tailor content accordingly by automatically scanning their newsfeeds, identifying people in photos and targeting them with precision ads. And now behind the scenes the social network's AI researchers are trying to take this technology to the next level--from pure data-crunching logic to a nuanced form of "common sense" rivaling that of humans. AI already lets machines do things like recognize faces and act as virtual assistants that can track down info on the Web for smartphone users. But to perform even these basic tasks the underlying learning algorithms rely on computer programs written by humans to feed them massive amounts of training data, a process known as machine learning.

WHEN the 2016 Wimbledon Championships start on June 27th millions of tennis fans will begin posting on social networks such as Twitter, Facebook and Instagram about everything from the matches to the attire, hairdos and headbands of their favourite players. The contest's organiser, the All England Lawn Tennis Club (AELTC), would quite like to know what the hottest topics are. So it is using a powerful computer to find out. That computer is Watson, an IBM machine which in 2011 famously won the American TV quiz "Jeopardy!" and nowadays resides as a cloud-computing service. The idea, says Alexandra Willis, the AELTC's digital supremo, is to use its machine learning and natural language-processing techniques to discover the most pressing topics of conversation among the vast output from fans. Knowing that, the club's editorial team--which provides content for Wimbledon's mobile app, its website and its video feeds--can respond quickly with relevant articles, posts, tweets, statistics and images.

XPRIZE has announced that registration is now open and guidelines are available for the 5 million IBM Watson AI XPRIZE, a four-year global competition challenging teams to develop and demonstrate how humans can collaborate with powerful artificial intelligence (AI) technologies to tackle the world's greatest challenges. The AI competition is XPRIZE's first open challenge where teams will define their own goals and create AI applications that solve some of humanity's most pressing challenges in areas such as healthcare, education, energy & environment, global development and exploration. "In the coming decade, as XPRIZE strives to achieve its impact mission through incentive competitions and crowd-sourcing, we see tremendous opportunity in this emerging generation of problem solvers to use AI to solve humanity's grandest challenges," said Marcus Shingles, CEO of XPRIZE. "The IBM Watson AI XPRIZE is intended to promote and progress the notion of'AI for impact' among the global bold innovator crowd, both the established community of practitioners, as well as encourage newcomers to experiment and ultimately demonstrate how AI can be used as a tool for good." Teams have until December 1, 2016 to register through the XPRIZE website for the four-year competition, and then will have until March 1, 2017 to submit a detailed development and testing plan for their proposed solution.

Romanian startup Grobyk is organizing ready-to-use, trending information from your chosen sources, using Artificial Intelligence algorithms. Their 3 words pitch is: Instant Relevant Research. Content marketers keep up with a lot of sources, from social media, blogs, news site and so on. Search engine trends are misleading. What's relevant are social media shares.