Semi-Supervised Learning with Deep Generative Models

The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones... (read more)

PDF Abstract NeurIPS 2014 PDF NeurIPS 2014 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification SVHN M1+M2 Percentage error 36.02 # 40
Image Classification SVHN M1+TSVM Percentage error 54.33 # 41
Image Classification SVHN M1+KNN Percentage error 65.63 # 42
Image Classification SVHN DGN Percentage error 36.02 # 40

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet