Mikko Honkala — accepted AI-conference papers

2015

Bidirectional Recurrent Neural Networks as Generative Models

Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, Juha T Karhunen

NeurIPS 2015poster

Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the model has been difficult. Recently, two different frameworks, G…

Cited by 172 Source ↗PDF ↗Scholar ↗

2015

Semi-supervised Learning with Ladder Networks

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

NeurIPS 2015poster

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 top of the Ladder ne…

Cited by 2042 Source ↗PDF ↗code ↗Scholar ↗