Harri Valpola

According to our database, Harri Valpola authored at least 37 papers between 2001 and 2019.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2019

Regularizing Trajectory Optimization with Denoising Autoencoders.

Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization.

Norman Di Palo, Harri Valpola

CoRR, 2018

2017

On the exact relationship between the denoising function and the data distribution.

Heikki Arponen, Matti Herranen, Harri Valpola

CoRR, 2017

Weight-averaged consistency targets improve semi-supervised deep learning results.

Antti Tarvainen, Harri Valpola

CoRR, 2017

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.

Antti Tarvainen, Harri Valpola

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Recurrent Ladder Networks.

Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hao, Antti Rasmus, Rinu Boney, Harri Valpola

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016

Tagger: Deep Unsupervised Perceptual Grouping.

Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Harri Valpola, Jürgen Schmidhuber

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

2015

Lateral Connections in Denoising Autoencoders Support Supervised Learning.

Antti Rasmus, Harri Valpola, Tapani Raiko

CoRR, 2015

Semi-Supervised Learning with Ladder Network.

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

CoRR, 2015

Denoising autoencoder with modulated lateral connections learns invariant representations of natural images.

Antti Rasmus, Tapani Raiko, Harri Valpola

Proceedings of the 3rd International Conference on Learning Representations, 2015

Semi-supervised Learning with Ladder Networks.

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

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

2014

From neural PCA to deep unsupervised learning.

Harri Valpola

CoRR, 2014

2013

Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities

Tommi Vatanen, Tapani Raiko, Harri Valpola, Yann LeCun

Proceedings of the 1st International Conference on Learning Representations, 2013

2012

Deep Learning Made Easier by Linear Transformations in Perceptrons.

Tapani Raiko, Harri Valpola, Yann LeCun

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

2009

Selective Attention Improves Learning.

Antti Yli-Krekola, Jaakko Särelä, Harri Valpola

Proceedings of the Artificial Neural Networks, 2009

2007

Compact Modeling of Data Using Independent Variable Group Analysis.

Esa Alhoniemi, Antti Honkela, Krista Lagus, Santeri Jeremias Seppä, Paul Wagner, Harri Valpola

IEEE Trans. Neural Networks, 2007

Building Blocks for Variational Bayesian Learning of Latent Variable Models.

Tapani Raiko, Harri Valpola, Markus Harva, Juha Karhunen

J. Mach. Learn. Res., 2007

Blind separation of nonlinear mixtures by variational Bayesian learning.

Antti Honkela, Harri Valpola, Alexander Ilin, Juha Karhunen

Digit. Signal Process., 2007

2006

Exploratory analysis of climate data using source separation methods.

Alexander Ilin, Harri Valpola, Erkki Oja

Neural Networks, 2006

Extraction of Components with Structured Variance.

Alexander Ilin, Harri Valpola, Erkki Oja

Proceedings of the International Joint Conference on Neural Networks, 2006

Separation of Nonlinear Image Mixtures by Denoising Source Separation.

Mariana S. C. Almeida, Harri Valpola, Jaakko Särelä

Proceedings of the Independent Component Analysis and Blind Signal Separation, 2006

2005

On the Effect of the Form of the Posterior Approximation in Variational Learning of ICA Models.

Alexander Ilin, Harri Valpola

Neural Process. Lett., 2005

Denoising Source Separation.

Jaakko Särelä, Harri Valpola

J. Mach. Learn. Res., 2005

Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework.

Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen

Proceedings of the UAI '05, 2005

Frequency-Based Separation of Climate Signals.

Alexander Ilin, Harri Valpola

Proceedings of the Knowledge Discovery in Databases: PKDD 2005, 2005

Development of Representations, Categories and Concepts - a Hypothesis.

Harri Valpola

Proceedings of the CIRA 2005, 2005

2004

Nonlinear dynamical factor analysis for state change detection.

Alexander Ilin, Harri Valpola, Erkki Oja

IEEE Trans. Neural Networks, 2004

Variational learning and bits-back coding: an information-theoretic view to Bayesian learning.

Antti Honkela, Harri Valpola

IEEE Trans. Neural Networks, 2004

Hierarchical models of variance sources.

Harri Valpola, Markus Harva, Juha Karhunen

Signal Process., 2004

Unsupervised Variational Bayesian Learning of Nonlinear Models.

Antti Honkela, Harri Valpola

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Accurate, Fast and Stable Denoising Source Separation Algorithms.

Harri Valpola, Jaakko Särelä

Proceedings of the Independent Component Analysis and Blind Signal Separation, 2004

Using Kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method.

Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola

Proceedings of the Independent Component Analysis and Blind Signal Separation, 2004

2003

Accelerating Cyclic Update Algorithms for Parameter Estimation by Pattern Searches.

Antti Honkela, Harri Valpola, Juha Karhunen

Neural Process. Lett., 2003

Independent component analysis for artefact separation in astrophysical images.

Maria Funaro, Erkki Oja, Harri Valpola

Neural Networks, 2003

Nonlinear Blind Source Separation by Variational Bayesian Learning.

Harri Valpola, Erkki Oja, Alexander Ilin, Antti Honkela, Juha Karhunen

IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 2003

2002

An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models.

Harri Valpola, Juha Karhunen

Neural Comput., 2002

2001

Independent Variable Group Analysis.

Krista Lagus, Esa Alhoniemi, Harri Valpola

Proceedings of the Artificial Neural Networks, 2001