Bridging the gap between human and machine vision

Suppose you look briefly from a few feet away at a person you have never met before. Step back a few paces and look again. Will you be able to recognize her face? “Yes, of course,” you probably are thinking. If this is true, it would mean that our visual system, having seen a single image of an object such as a specific face, recognizes it robustly despite changes to the object’s position and scale, for example. On the other hand, we know that state-of-the-art classifiers, such as vanilla deep networks, will fail this simple test. In order to recognize a specific face under a range of transformations, neural networks need to be trained with many examples of the face under the different conditions. In other words, they can achieve invariance through memorization, but cannot do it if only one image is available. Thus, understanding how human vision can pull Continue reading Bridging the gap between human and machine vision

Brainstorming energy-saving hacks on Satori, MIT’s new supercomputer

Mohammad Haft-Javaherian planned to spend an hour at the Green AI Hackathon — just long enough to get acquainted with MIT’s new supercomputer, Satori. Three days later, he walked away with $1,000 for his winning strategy to shrink the carbon footprint of artificial intelligence models trained to detect heart disease.  “I never thought about the kilowatt-hours I was using,” he says. “But this hackathon gave me a chance to look at my carbon footprint and find ways to trade a small amount of model accuracy for big energy savings.”  Haft-Javaherian was among six teams to earn prizes at a hackathon co-sponsored by the MIT Research Computing Project and MIT-IBM Watson AI Lab Jan. 28-30. The event was meant to familiarize students with Satori, the computing cluster IBM donated to MIT last year, and to inspire new techniques for building energy-efficient AI models that put less planet-warming carbon dioxide into the air.  The event was also a celebration Continue reading Brainstorming energy-saving hacks on Satori, MIT’s new supercomputer

How to Program Sony’s Robot Dog Aibo

The Sony Aibo has been the most sophisticated home robot that you can buy for an astonishing 20 years. The first Aibo went on sale in 1999, and even though there was a dozen year-long gap between 2005’s ERS-7 and the latest ERS-1000, there was really no successful consumer robot over that intervening time that seriously challenged the Aibo. Part of what made Aibo special was how open Sony was user customization and programmability. Aibo served as the RoboCup Standard Platform for a decade, providing an accessible hardware platform that leveled the playing field for robotic soccer. Designed to stand up to the rigors of use by unsupervised consumers (and, presumably, their kids), Aibo offered both durability and versatility that compared fairly well to later, much more expensive robots like Nao.  Aibo ERS-1000: The newest model The newest Aibo, the ERS-1000, was announced in late 2017 and is now available for US Continue reading How to Program Sony’s Robot Dog Aibo