default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDHarri Valpola
Person information
- affiliation: Aalto University, Finland
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2010 – 2019
- 2019
[c20]Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola:
Regularizing Trajectory Optimization with Denoising Autoencoders. NeurIPS 2019: 2855-2865- [i10]Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola:
Regularizing Trajectory Optimization with Denoising Autoencoders. CoRR abs/1903.11981 (2019) - 2018
- [i9]Norman Di Palo, Harri Valpola:
Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization. CoRR abs/1812.03955 (2018) - 2017
- [c19]Antti Tarvainen, Harri Valpola:
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. ICLR (Workshop) 2017 - [c18]Antti Tarvainen, Harri Valpola:
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NIPS 2017: 1195-1204 - [c17]Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hao, Antti Rasmus, Rinu Boney, Harri Valpola:
Recurrent Ladder Networks. NIPS 2017: 6009-6019 - [i8]Antti Tarvainen, Harri Valpola:
Weight-averaged consistency targets improve semi-supervised deep learning results. CoRR abs/1703.01780 (2017) - [i7]Alexander Ilin, Isabeau Prémont-Schwarz, Tele Hotloo Hao, Antti Rasmus, Rinu Boney, Harri Valpola:
Recurrent Ladder Networks. CoRR abs/1707.09219 (2017) - [i6]Heikki Arponen, Matti Herranen, Harri Valpola:
On the exact relationship between the denoising function and the data distribution. CoRR abs/1709.02797 (2017) - 2016
- [c16]Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Harri Valpola, Jürgen Schmidhuber:
Tagger: Deep Unsupervised Perceptual Grouping. NIPS 2016: 4484-4492 - [i5]Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Jürgen Schmidhuber, Harri Valpola:
Tagger: Deep Unsupervised Perceptual Grouping. CoRR abs/1606.06724 (2016) - 2015
- [c15]Antti Rasmus, Mathias Berglund, Mikko Honkala, Harri Valpola, Tapani Raiko:
Semi-supervised Learning with Ladder Networks. NIPS 2015: 3546-3554 - [c14]Antti Rasmus, Tapani Raiko, Harri Valpola:
Denoising autoencoder with modulated lateral connections learns invariant representations of natural images. ICLR (Workshop) 2015 - [i4]Antti Rasmus, Harri Valpola, Tapani Raiko:
Lateral Connections in Denoising Autoencoders Support Supervised Learning. CoRR abs/1504.08215 (2015) - [i3]Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko:
Semi-Supervised Learning with Ladder Network. CoRR abs/1507.02672 (2015) - 2014
- [i2]Harri Valpola:
From neural PCA to deep unsupervised learning. CoRR abs/1411.7783 (2014) - 2013
- [c13]Tommi Vatanen
, Tapani Raiko, Harri Valpola, Yann LeCun:
Pushing Stochastic Gradient towards Second-Order Methods - Backpropagation Learning with Transformations in Nonlinearities. ICONIP (1) 2013: 442-449 - [c12]Tommi Vatanen, Tapani Raiko, Harri Valpola, Yann LeCun:
Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities. ICLR (Workshop Poster) 2013 - 2012
- [c11]Tapani Raiko, Harri Valpola, Yann LeCun:
Deep Learning Made Easier by Linear Transformations in Perceptrons. AISTATS 2012: 924-932 - [i1]Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen:
Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework. CoRR abs/1207.1380 (2012)
2000 – 2009
- 2009
- [c10]Antti Yli-Krekola, Jaakko Särelä, Harri Valpola:
Selective Attention Improves Learning. ICANN (2) 2009: 285-294 - 2007
- [j13]Antti Honkela, Harri Valpola, Alexander Ilin, Juha Karhunen:
Blind separation of nonlinear mixtures by variational Bayesian learning. Digit. Signal Process. 17(5): 914-934 (2007) - [j12]Tapani Raiko, Harri Valpola, Markus Harva, Juha Karhunen:
Building Blocks for Variational Bayesian Learning of Latent Variable Models. J. Mach. Learn. Res. 8: 155-201 (2007) - [j11]Esa Alhoniemi, Antti Honkela, Krista Lagus, Santeri Jeremias Seppä, Paul Wagner, Harri Valpola:
Compact Modeling of Data Using Independent Variable Group Analysis. IEEE Trans. Neural Networks 18(6): 1762-1776 (2007) - 2006
- [j10]Alexander Ilin, Harri Valpola, Erkki Oja:
Exploratory analysis of climate data using source separation methods. Neural Networks 19(2): 155-167 (2006) - [c9]Mariana S. C. Almeida, Harri Valpola, Jaakko Särelä:
Separation of Nonlinear Image Mixtures by Denoising Source Separation. ICA 2006: 8-15 - [c8]Alexander Ilin, Harri Valpola, Erkki Oja:
Extraction of Components with Structured Variance. IJCNN 2006: 5110-5117 - 2005
- [j9]Jaakko Särelä, Harri Valpola:
Denoising Source Separation. J. Mach. Learn. Res. 6: 233-272 (2005) - [j8]Alexander Ilin, Harri Valpola:
On the Effect of the Form of the Posterior Approximation in Variational Learning of ICA Models. Neural Process. Lett. 22(2): 183-204 (2005) - [c7]Harri Valpola:
Development of Representations, Categories and Concepts - a Hypothesis. CIRA 2005: 593-599 - [c6]Alexander Ilin, Harri Valpola:
Frequency-Based Separation of Climate Signals. PKDD 2005: 519-526 - [c5]Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen:
Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework. UAI 2005: 259-266 - 2004
- [j7]Harri Valpola, Markus Harva, Juha Karhunen:
Hierarchical models of variance sources. Signal Process. 84(2): 267-282 (2004) - [j6]Alexander Ilin, Harri Valpola, Erkki Oja:
Nonlinear dynamical factor analysis for state change detection. IEEE Trans. Neural Networks 15(3): 559-575 (2004) - [j5]Antti Honkela, Harri Valpola:
Variational learning and bits-back coding: an information-theoretic view to Bayesian learning. IEEE Trans. Neural Networks 15(4): 800-810 (2004) - [c4]Harri Valpola, Jaakko Särelä:
Accurate, Fast and Stable Denoising Source Separation Algorithms. ICA 2004: 65-72 - [c3]Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola:
Using Kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method. ICA 2004: 790-797 - [c2]Antti Honkela, Harri Valpola:
Unsupervised Variational Bayesian Learning of Nonlinear Models. NIPS 2004: 593-600 - 2003
- [j4]Harri Valpola, Erkki Oja, Alexander Ilin, Antti Honkela, Juha Karhunen:
Nonlinear Blind Source Separation by Variational Bayesian Learning. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 86-A(3): 532-541 (2003) - [j3]Maria Funaro, Erkki Oja, Harri Valpola:
Independent component analysis for artefact separation in astrophysical images. Neural Networks 16(3-4): 469-478 (2003) - [j2]Antti Honkela, Harri Valpola, Juha Karhunen:
Accelerating Cyclic Update Algorithms for Parameter Estimation by Pattern Searches. Neural Process. Lett. 17(2): 191-203 (2003) - 2002
- [j1]Harri Valpola, Juha Karhunen:
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models. Neural Comput. 14(11): 2647-2692 (2002) - 2001
- [c1]Krista Lagus, Esa Alhoniemi, Harri Valpola:
Independent Variable Group Analysis. ICANN 2001: 203-210
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-13 00:44 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
