Timezone: »

Semi-supervised Learning with Ladder Networks
Antti Rasmus · Mathias Berglund · Mikko Honkala · Harri Valpola · Tapani Raiko

Thu Dec 10 08:00 AM -- 12:00 PM (PST) @ 210 C #3

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 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.

Author Information

Antti Rasmus (The Curious AI Company)
Mathias Berglund (Aalto University)
Mikko Honkala (Nokia Labs)
Harri Valpola (The Curious AI Company)
Tapani Raiko (Aalto University, The Curious AI Company)

More from the Same Authors