no code implementations • 19 Apr 2021 • Shiyu Duan, Spencer Chang, Jose C. Principe
We call this statistic "sufficiently-labeled data" and prove its sufficiency and efficiency for finding the optimal hidden representations, on which competent classifier heads can be trained using as few as a single randomly-chosen fully-labeled example per class.
no code implementations • 28 Sep 2017 • Spencer Chang, Timothy Cohen, Bryan Ostdiek
Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency.