Understanding Representation Learnability of Nonlinear Self-Supervised Learning

1 code implementation • 6 Jan 2024 • Ruofeng Yang, Xiangyuan Li, Bo Jiang, Shuai Li

There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, treating the nonlinear neural network as a ``black box".

Self-Supervised Learning