• Home
  • Extra seminar: Tapani Raiko – Semi-Supervised Deep Learning with Ladder Networks

Extra seminar: Tapani Raiko – Semi-Supervised Deep Learning with Ladder Networks

SEMINAR

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 pretraining. The model structure is an autoencoder with skip connections from the encoder to decoder and the learning task is similar to that in denoising autoencoders but applied to every layer. The skip connections relieve the pressure to represent details at the higher layers of the model because, through the skip connections, the decoder can recover any details discarded by the encoder. We show that the resulting model reaches state-of-the-art performance in various tasks: MNIST and CIFAR-10 classification in a semi-supervised setting and permutation invariant MNIST in both semi-supervised and full-labels setting.

Date: 2015-11-20 13:30 - 15:00

Location: room 8103, EDIT Building, Hörsalsvägen 11, Chalmers Johanneberg

Permalink

add to Outlook/iCal

To the top

Page updated: 2015-11-06 16:24

Send as email
Print page
Show as pdf

X
Loading