SOTAVerified

Semi-Supervised Learning with Ladder Networks

2015-07-09NeurIPS 2015Code Available1· sign in to hype

Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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.

Tasks

General ClassificationSemi-Supervised Image Classification

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CIFAR-10, 4000 LabelsΓ-modelPercentage error20.4—Unverified

Reproductions