arXiv (Cornell University) · 2015 · 597 citations · 29 references
ComputingComputer ScienceArtificial IntelligenceComputer VisionMachine LearningDeep LearningNeural NetworksPattern RecognitionSemi-supervised LearningSupervised LearningUnsupervised LearningDeep Learning-based ClassificationNetwork Cost FunctionsSemi-supervised ClassificationSemi-supervised Image ClassificationSemi-supervised ModelsSemi-supervised Representation Learning
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.
29
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Combining labeled and unlabeled data with co-training
Avrim Blum, Tom M. Mitchell · 1998 · 5.6K citations · Full text