The paper "Model Compression" is available here: https://www.cs.cornell.edu/ Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_c... The thumbnail background image was created by John Lord - https://flic.kr/p/nVUaB

Today on In Case You Missed It: MIT researchers made a deep learning vision system watch TV and it learned to predict when people are going to kiss, shake hands, high five or hug. Georgia Tech scientists teamed up with others to figure out how to create 3D images of microscopic cells, by giving them a selfie mirror. To check out the WalMart fireworks video in full, click here. As always, please share any interesting tech or science videos you find by using the #ICYMI hashtag on Twitter for @mskerryd.

Using cognitive science theories, Forbus and his collaborators have developed a model that could give computers the ability to reason more like humans and even make moral decisions. Called the structure-mapping engine (SME), the new model is capable of analogical problem solving, including capturing the way humans spontaneously use analogies between situations to solve moral dilemmas. "In terms of thinking like humans, analogies are where it's at," said Forbus, Walter P. Murphy Professor of Electrical Engineering and Computer Science in Northwestern's McCormick School of Engineering. "Humans use relational statements fluidly to describe things, solve problems, indicate causality, and weigh moral dilemmas." The theory underlying the model is psychologist Dedre Gentner's structure-mapping theory of analogy and similarity, which has been used to explain and predict many psychology phenomena.

Angela Duckworth, in her best-selling book, "Grit: The Power of Passion and Perseverance," celebrates a man whom she calls a "grit paragon": Pete Carroll, the coach of the Seattle Seahawks, who led the team to a Super Bowl victory in 2014. It seems that Carroll had seen Duckworth's TED talk nine months earlier and got in touch, eager to reassure her that building grit was exactly what the Seahawks culture was all about. Two years later, Duckworth visited the Seahawks training camp. She lectured to the team's players and coaching staff. The subject was . . . Duckworth was impressed by the Seahawks, and she quotes sentiments that are characteristic of the Carroll ethos: "Compete in everything you do. Since the team trains ferociously all the time--going all out, for instance, in bone-crunching intra-squad practice sessions--this conversation may not have been entirely necessary. Duckworth, a professor of psychology at the University of Pennsylvania, finds grit in the best possible places. Her grit obsession, as she recounts, began at least a decade earlier. As a graduate student, she visited West Point, where each year twelve hundred new cadets go through a gruelling seven-week training regimen ("Barracks Beast") before entering freshman year. Most make it through, though some do not. Duckworth could make some guesses. In this same period, eager to find out what made top people successful, she was interviewing "leaders in business, art, athletics, journalism, academia, medicine and law." She discovered that "the highly successful had a kind of ferocious determination that played out in two ways.

Northwestern University's Ken Forbus is closing the gap between humans and machines. Using cognitive science theories, Forbus and his collaborators have developed a model that could give computers the ability to reason more like humans and even make moral decisions. Called the structure-mapping engine (SME), the new model is capable of analogical problem solving, including capturing the way humans spontaneously use analogies between situations to solve moral dilemmas. "In terms of thinking like humans, analogies are where it's at," said Forbus, Walter P. Murphy Professor of Electrical Engineering and Computer Science in Northwestern's McCormick School of Engineering. "Humans use relational statements fluidly to describe things, solve problems, indicate causality, and weigh moral dilemmas."

As a High School student Carlton had been withdrawn and quiet, unsocial and uninvolved. One of his teachers was convinced that he was using drugs because he was so pale and tired. In reality, he had been up late into the night, designing, building and refining his electrically independent computer. He drew his own blood for it, leading to symptoms of anemia. His prototype was, in retrospect, an archaic fossil as soon as it was operational, but he won a National competition with it. He won because his design exemplified the philosophical goals of the contest: energy efficiency.

In this paper we model the problem of learning preferences of a population as an active learning problem. We propose an algorithm can adaptively choose pairs of items to show to users coming from a heterogeneous population, and use the obtained reward to decide which pair of items to show next. We provide computationally efficient algorithms with provable sample complexity guarantees for this problem in both the noiseless and noisy cases. In the process of establishing sample complexity guarantees for our algorithms, we establish new results using a Nystr{\"o}m-like method which can be of independent interest. We supplement our theoretical results with experimental comparisons.

The traditional definition of artificial intelligence is the ability of machines to execute tasks and solve problems in ways normally attributed to humans. Some tasks that we consider simple--recognizing an object in a photo, driving a car--are incredibly complex for AI. Machines can surpass us when it comes to things like playing chess, but those machines are limited by the manual nature of their programming; a 30 gadget can beat us at a board game, but it can't do--or learn to do--anything else. This is where machine learning comes in. Show millions of cat photos to a machine, and it will hone its algorithms to improve at recognizing pictures of cats.

A remarkable feature of human and animal intelligence is the ability to autonomously acquire new behaviors. This research is concerned with designing algorithms that aim to bring this ability to robots and simulated characters. Levine will describe a class of guided policy search algorithms that tackle this challenge by transforming the task of learning control policies into a supervised learning problem, with supervision provided by simple, efficient trajectory-centric methods.

Learning needs to be less like memorization, and more like…Angry Birds. Half of school dropouts name boredom as the number one reason they left. The post is about why the future of education will be about flipping our current model on its head and about how key exponential technologies like AI, VR and gamification are going to drive a revolution in education. In the traditional education system, you start at an "A," and every time you get something wrong, your score gets lower and lower. You start with zero, and every time you come up with something right, your score gets higher and higher.