Semi-Supervised Learning via New Deep Network Inversion

11/12/2017
by   Randall Balestriero, et al.
0

We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching 99.14% of test set accuracy while using 5 labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset