We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes acquisition costs whilst still yielding accurate predictions. The AFA framework can be useful in a myriad of domains, including health care applications where the cost of acquiring additional features for a patient (in terms of time, money, risk, etc.) can be weighed against the expected improvement to diagnostic performance. Previous approaches for AFA have employed either: deep learning RL techniques, which have difficulty training policies in the AFA MDP due to sparse rewards and a complicated action space; deep learning surrogate generative models, which require modeling complicated multidimensional conditional distributions; or greedy policies, which fail to account for how joint feature acquisitions can be informative together for better predictions. In this work we show that we can bypass many of these challenges with a novel, nonparametric oracle based approach, which we coin the acquisition conditioned oracle (ACO). Extensive experiments show the superiority of the ACO to state-of-the-art AFA methods when acquiring features for both predictions and general decision-making.

Astronaut Danny Olivas joins ISI's Visual Intelligence and Multimedia Analytics Laboratory (VIMAL) to look for ways to use AI in space. John Daniel "Danny" Olivas, former NASA astronaut and current member of the NASA Advisory Council, has joined the staff of the Visual Intelligence and Multimedia Analytics Laboratory (VIMAL) of USC's Information Sciences Institute (ISI) as Co-Director for AI Initiatives in Space. A veteran of space shuttle missions in 2007 and 2009, he is the recipient of two NASA Space Flight Medals and the NASA Exceptional Service and Exceptional Achievement Medals. Olivas completed five space walks totaling over 34 hours outside of the International Space Station. His expertise in space is rivaled only by his passion for it, and he brings both to his new role.

Most artificial intelligence is still built on a foundation of human toil. Peer inside an AI algorithm and you'll find something constructed using data that was curated and labeled by an army of human workers. Now, Facebook has shown how some AI algorithms can learn to do useful work with far less human help. The company built an algorithm that learned to recognize objects in images with little help from labels. The Facebook algorithm, called Seer (for SElf-supERvised), fed on more than a billion images scraped from Instagram, deciding for itself which objects look alike. Images with whiskers, fur, and pointy ears, for example, were collected into one pile.

Most artificial intelligence is still built on a foundation of human toil. Peer inside an AI algorithm and you'll find something constructed using data that was curated and labeled by an army of human workers. Now, Facebook has shown how some AI algorithms can learn to do useful work with far less human help. The company built an algorithm that learned to recognize objects in images with little help from labels. The Facebook algorithm, called Seer (for SElf-supERvised), fed on more than a billion images scraped from Instagram, deciding for itself which objects look alike.

The ability to reason abstractly about events as they unfold is a defining feature of human intelligence. We know instinctively that crying and writing are means of communicating, and that a panda falling from a tree and a plane landing are variations on descending. Organizing the world into abstract categories does not come easily to computers, but in recent years researchers have inched closer by training machine learning models on words and images infused with structural information about the world, and how objects, animals, and actions relate. In a new study at the European Conference on Computer Vision this month, researchers unveiled a hybrid language-vision model that can compare and contrast a set of dynamic events captured on video to tease out the high-level concepts connecting them. Their model did as well as or better than humans at two types of visual reasoning tasks--picking the video that conceptually best completes the set, and picking the video that doesn't fit.

The ability to reason abstractly about events as they unfold is a defining feature of human intelligence. We know instinctively that crying and writing are means of communicating, and that a panda falling from a tree and a plane landing are variations on descending. Organizing the world into abstract categories does not come easily to computers, but in recent years researchers have inched closer by training machine learning models on words and images infused with structural information about the world, and how objects, animals, and actions relate. In a new study at the European Conference on Computer Vision this month, researchers unveiled a hybrid language-vision model that can compare and contrast a set of dynamic events captured on video to tease out the high-level concepts connecting them. Their model did as well as or better than humans at two types of visual reasoning tasks -- picking the video that conceptually best completes the set, and picking the video that doesn't fit.

From the "Mona Lisa" to the "Girl with a Pearl Earring," some images linger in the mind long after others have faded. Ask an artist why, and you might hear some generally-accepted principles for making memorable art. Now there's an easier way to learn: ask an artificial intelligence model to draw an example. A new study using machine learning to generate images ranging from a memorable cheeseburger to a forgettable cup of coffee shows in close detail what makes a portrait or scene stand out. The images that human subjects in the study remembered best featured bright colors, simple backgrounds, and subjects that were centered prominently in the frame.

By Meg Murphy A person watching videos that show things opening -- a door, a book, curtains, a blooming flower, a yawning dog -- easily understands the same type of action is depicted in each clip. "Computer models fail miserably to identify these things. How do humans do it so effortlessly?" asks Dan Gutfreund, a principal investigator at the MIT-IBM Watson AI Laboratory and a staff member at IBM Research. "We process information as it happens in space and time. How can we teach computer models to do that?"

Scientists are using emerging artificial intelligence (AI) networks to enhance their understanding of one of the most elusive intelligence systems: the human brain. The researchers are learning much about the role of contextual clues in human image recognition. By using artificial neurons - essentially lines of code, software - with neural network models, they can parse out the various elements that go into recognising a specific place or object. "The fundamental questions cognitive neuroscientists and computer scientists seek to answer are similar," said Aude Oliva from the Massachusetts Institute of Technology (MIT) in the US. "They have a complex system made of components - for one, it is called neurons and for the other, it is called units - and we are doing experiments to try to determine what those components calculate," said Oliva, who presented the research at the annual meeting of the Cognitive Neuroscience Society (CNS).