A new approach could lower computing costs and increase accessibility to state-of-the-art natural language processing.
WNCG student Tianlong Chen is the lead author of a study in artificial intelligence that posits that hidden within massive neural networks, leaner subnetworks exist that can complete the same task more efficiently. The study is co-authored by WNCG assistant professor Zhangyang "Atlas" Wang, along with Jonathan Frankle of MIT CSAIL, and Shiyu Chang, Sijia Liu, and Yang Zhang, all of the MIT-IBM Watson AI Lab.