EECS Department Colloquium Series
Humans, Devices, and How They Live Together
Wednesday, November 20, 2013
Over the years she also discovered how many disabled people could benefit by advances such as the robotic hand, and took a deep interest in neuroscience as a discipline that could help improve the prospects of the physically and mentally disabled.
After a stint on the faculty at the University of Washington, she recently left to join Nest Labs, which is headed up by Tony Fadell, the former Apple executive who was instrumental in developing the iPod and the iPhone.
Nest’s thermostat is quite reminiscent of Apple products in the simplicity and elegance of its design, combined with the sophistication of its technology. “The idea was to take what is currently an ugly beige product we don't even look at, and make it beautiful, with an easy-to-use user interface, plus it’s smart and you can program it from anywhere on your smartphone,” explains Matsuoka. The Nest thermostat learns from you. When you feel cold, turn it up; when you feel warm, turn it down. The device tracks your habits to recognize when you’re home or away, awake or asleep, active or sedentary. It has five sensors measuring the temperature, humidity, light, near-field motion detector, and far field motion sensor. It detects your presence as a large water mass with a specific body temperature. It is constantly learning from your patterns of behavior. “How does it learn? It looks to see what you do in the morning, when you usually get up, and later when do you get home at night. It calculates the probabilities around all of that," Matsuoka explains. “From sensor data, we know that people are very regular in our habits. This allows our algorithm to be predictive and anticipate when to adjust the temperature in your house.”
Matsuoka cautions that people have to take an active role at first by interacting with the thermostat. “It learns like humans learn – very aggressively at first and then it slows down. So you have to teach it – it’s not a passive learning experience. We ask people to teach it well. After a few days, it will respond very well.”
For Matsuoka, the Nest position represents a merging of her intellectual interests. “I’m always trying to combine the different paths I have taken. Here, I work at the intersection of human learning and machine (device) learning. That’s the sweet spot – to help people be who they want to be. People want to be green but they don’t necessarily know how to be green. Technology can help you accomplish that goal.”
Yoky Matsuoka is VP of Technology at Nest Labs (www.nest.com). She received her Ph.D. at MIT in Electrical Engineering and Computer Science in the fields of Artificial Intelligence and Computational Neuroscience. She received an M.S. from MIT and a B.S. from UC Berkeley, both in EECS. She was also a Postdoctoral Fellow in the Brain and Cognitive Sciences at MIT and in Mechanical Engineering at Harvard University. She was Torode Family Endowed Career Development Professor of Computer Science and Engineering at the University of Washington, Director of NSF ERC Center for Sensorimotor Neural Engineering, and Ana Loomis McCandless Professor of Robotics and Mechanical Engineering at Carnegie Mellon University. Her work has been recognized with a MacArthur Fellowship, acclaimed as one of “The Brilliant Ten” in Popular Science Magazine, “Top 10 Women to Watch in 2010” by Barbie, and "Power 25” in Seattle Magazine.
|Return to EECS Joint Colloquium|