Semi-Supervised Learning with Ladder Networks
Neural and Evolutionary Computing
2015-11-25 v2 Machine Learning
Machine Learning
Abstract
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (2015), which we extend by combining the model with supervision. We show that the resulting model reaches state-of-the-art performance in semi-supervised MNIST and CIFAR-10 classification, in addition to permutation-invariant MNIST classification with all labels.
Cite
@article{arxiv.1507.02672,
title = {Semi-Supervised Learning with Ladder Networks},
author = {Antti Rasmus and Harri Valpola and Mikko Honkala and Mathias Berglund and Tapani Raiko},
journal= {arXiv preprint arXiv:1507.02672},
year = {2015}
}
Comments
Revised denoising function, updated results, fixed typos