Bringing deep learning to life | School of Engineering - MIT News

MIT duo uses music, videos, and real-world examples to teach students the foundations of artificial intelligence, according to Kim Martineau, MIT Quest for Intelligence.

The instructors and a cadre of teaching students are on hand to help with questions after class. Here, Ava Soleimany explains back propagation.

Photo: Gretchen Ertl

Gaby Ecanow loves listening to music, but never considered writing her own until taking 6.S191 (Introduction to Deep Learning). By her second class, the second-year MIT student had composed an original Irish folk song with the help of a recurrent neural network, and was considering how to adapt the model to create her own Louis the Child-inspired dance beats.

“It was cool,” she says. “It didn’t sound at all like a machine had made it.” 

This year, 6.S191 kicked off as usual, with students spilling into the aisles of Stata Center’s Kirsch Auditorium during Independent Activities Period (IAP). But the opening lecture featured a twist: a recorded welcome from former President Barack Obama. The video was quickly revealed to be an AI-generated fabrication, one of many twists that Alexander Amini ’17 and Ava Soleimany ’16 introduce throughout their for-credit course to make the equations and code come alive...

“There’s still work to be done, but I’m excited by how far I was able to get in three days,” he says. “Having easy-to-follow examples in TensorFlow and Keras helped me understand how to actually build and train these models myself.” He plans to continue the work in his current lab rotation with Bonnie Berger, the Simons Professor of Mathematics in EECS and the Computer Science and Artificial Intelligence Laboratory (CSAIL)...

With 350 students taking the live course each year, and more than a million people who have watched the lectures online, Amini and Soleimany have become prominent ambassadors for deep learning. Yet, it was tennis that first brought them together. 
Read more... 

Source: MIT News