Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Semi-Supervised Learning via New Deep Network Inversion
Balestriero R., Roger V., Glotin H., Baraniuk R.
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract: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 reaches current state-of-the-art methods on MNIST and provides reasonable performances on SVHN and CIFAR10. Through the introduced method, residual networks are for the first time applied to semi-supervised tasks. 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.
TL;DR:We exploit an inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework applicable to many topologies.
Keywords:inversion scheme, deep neural networks, semi-supervised learning, MNIST, SVHN, CIFAR10
Enter your feedback below and we'll get back to you as soon as possible.