Statistical-Mechanical Analysis Connecting Supervised Learning and Semi-Supervised Learning
Takashi Fujii, Hidetaka Ito, Seiji Miyoshi · Journal of the Physical Society of Japan · 2017
The generalization performance of semi-supervised learning is analyzed in the framework of online learning using the statistical-mechanical method. We derive deterministically formed simultaneous differential equations that describe the dynamical behaviors of order parameters using the self-averaging property under the thermodynamic limit. By generalizing the number of labeled data, the derived theory connects supervised learning and semi-supervised learning.