Seuraa
Harri Valpola
Harri Valpola
Apple
Vahvistettu sähköpostiosoite verkkotunnuksessa apple.com - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
Weight-averaged consistency targets improve semi-supervised deep learning results
A Tarvainen, H Valpola
arXiv preprint arXiv:1703.01780, 2017
3127*2017
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
A Tarvainen, H Valpola
Advances in neural information processing systems, 1195-1204, 2017
31242017
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
A Tarvainen, H Valpola
Advances in neural information processing systems, 1195-1204, 2017
31242017
Semi-Supervised Learning with Ladder Networks
A Rasmus, H Valpola, M Honkala, M Berglund, T Raiko
arXiv preprint arXiv:1507.02672, 2015
15092015
Deep learning made easier by linear transformations in perceptrons
T Raiko, H Valpola, Y LeCun
Artificial Intelligence and Statistics, 924-932, 2012
12432012
Pushing stochastic gradient towards second-order methods–backpropagation learning with transformations in nonlinearities
T Vatanen, T Raiko, H Valpola, Y LeCun
Neural Information Processing: 20th International Conference, ICONIP 2013 …, 2013
10452013
Ensemble learning
H Lappalainen, J Miskin
Advances in Independent Component Analysis, 75-92, 2000
334*2000
Bayesian non-linear independent component analysis by multi-layer perceptrons
H Lappalainen, A Honkela
Advances in independent component analysis, 93-121, 2000
256*2000
Denoising Source Separation.
J Särelä, H Valpola
Journal of Machine Learning Research 6 (3), 2005
2222005
Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM
T Kohonen, S Kaski, H Lappalainen
Neural computation 9 (6), 1321-1344, 1997
2171997
From neural PCA to deep unsupervised learning
H Valpola
Advances in Independent Component Analysis and Learning Machines, 143-171, 2015
2162015
An unsupervised ensemble learning method for nonlinear dynamic state-space models
H Valpola, J Karhunen
Neural computation 14 (11), 2647-2692, 2002
1752002
Tagger: Deep unsupervised perceptual grouping
K Greff, A Rasmus, M Berglund, T Hao, H Valpola, J Schmidhuber
Advances in Neural Information Processing Systems 29, 4484-4492, 2016
1432016
Variational learning and bits-back coding: an information-theoretic view to Bayesian learning
A Honkela, H Valpola
IEEE Transactions on Neural Networks 15 (4), 800-810, 2004
832004
Ensemble learning for independent component analysis
H Lappalainen
Proc. Int. Workshop on Independent Component Analysis and Signal Separation …, 1999
761999
Method for the selection of physical objects in a robot system
H Valpola, T Lukka
US Patent 9,050,719, 2015
692015
Method for the selection of physical objects in a robot system
H Valpola, T Lukka
US Patent 9,050,719, 2015
692015
Unsupervised variational Bayesian learning of nonlinear models
A Honkela, H Valpola
Advances in neural information processing systems 17, 593-600, 2004
632004
Bayesian ensemble learning for nonlinear factor analysis
H Valpola
Finnish Academy of Technology, 2000
582000
Hierarchical models of variance sources
H Valpola, M Harva, J Karhunen
Signal Processing 84 (2), 267-282, 2004
572004
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20