Harri Valpola - RankMe

49 papers A* 2A 2B 2C 1Journal 27Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories. CoRR Ya Gao, Kalle Kujanpää, Pekka Marttinen, Harri Valpola, Alexander Ilin
2026	A*	`conf`	Tuning Qwen2.5-VL to Improve Its Web Interaction Skills. WWW Alexandra Yakovleva, Henrik Pärssinen, Harri Valpola, Juho Kannala, Alexander Ilin
2025	J	`jnl`	Efficient Knowledge Injection in LLMs via Self-Distillation. Trans. Mach. Learn. Res. Kalle Kujanpää, Pekka Marttinen, Harri Valpola, Alexander Ilin
2025	J	`jnl`	Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization. CoRR Minttu Alakuijala, Ya Gao, Georgy Ananov, Samuel Kaski, Pekka Marttinen, Alexander Ilin, Harri Valpola
2024	J	`jnl`	Knowledge Injection via Prompt Distillation. CoRR Kalle Kujanpää, Harri Valpola, Alexander Ilin
2019	A*	`conf`	Regularizing Trajectory Optimization with Denoising Autoencoders. NeurIPS Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola
2019	J	`jnl`	Regularizing Trajectory Optimization with Denoising Autoencoders. CoRR Rinu Boney, Norman Di Palo, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola
2018	J	`jnl`	Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization. CoRR Norman Di Palo, Harri Valpola
2017	—	`conf`	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. ICLR (Workshop) Antti Tarvainen, Harri Valpola
2017	—	`conf`	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NIPS Antti Tarvainen, Harri Valpola
2017	J	`jnl`	On the exact relationship between the denoising function and the data distribution. CoRR Heikki Arponen, Matti Herranen, Harri Valpola
2017	—	`conf`	Recurrent Ladder Networks. NIPS Isabeau Prémont-Schwarz, Alexander Ilin, Tele Hao, Antti Rasmus, Rinu Boney, Harri Valpola
2017	J	`jnl`	Recurrent Ladder Networks. CoRR Alexander Ilin, Isabeau Prémont-Schwarz, Tele Hotloo Hao, Antti Rasmus, Rinu Boney, Harri Valpola
2017	J	`jnl`	Weight-averaged consistency targets improve semi-supervised deep learning results. CoRR Antti Tarvainen, Harri Valpola
2016	—	`conf`	Tagger: Deep Unsupervised Perceptual Grouping. NIPS Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Harri Valpola, Jürgen Schmidhuber
2016	J	`jnl`	Tagger: Deep Unsupervised Perceptual Grouping. CoRR Klaus Greff, Antti Rasmus, Mathias Berglund, Tele Hotloo Hao, Jürgen Schmidhuber, Harri Valpola
2015	—	`conf`	Denoising autoencoder with modulated lateral connections learns invariant representations of natural images. ICLR (Workshop) Antti Rasmus, Tapani Raiko, Harri Valpola
2015	J	`jnl`	Lateral Connections in Denoising Autoencoders Support Supervised Learning. CoRR Antti Rasmus, Harri Valpola, Tapani Raiko
2015	J	`jnl`	Semi-Supervised Learning with Ladder Network. CoRR Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko
2015	—	`conf`	Semi-supervised Learning with Ladder Networks. NIPS Antti Rasmus, Mathias Berglund, Mikko Honkala, Harri Valpola, Tapani Raiko
2014	J	`jnl`	From neural PCA to deep unsupervised learning. CoRR Harri Valpola
2013	—	`conf`	Pushing Stochastic Gradient towards Second-Order Methods - Backpropagation Learning with Transformations in Nonlinearities. ICONIP (1) Tommi Vatanen, Tapani Raiko, Harri Valpola, Yann LeCun
2013	—	`conf`	Pushing Stochastic Gradient towards Second-Order Methods -- Backpropagation Learning with Transformations in Nonlinearities ICLR (Workshop Poster) Tommi Vatanen, Tapani Raiko, Harri Valpola, Yann LeCun
2012	J	`jnl`	Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework CoRR Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen
2012	A	`conf`	Deep Learning Made Easier by Linear Transformations in Perceptrons. AISTATS Tapani Raiko, Harri Valpola, Yann LeCun
2009	—	`conf`	Selective Attention Improves Learning. ICANN (2) Antti Yli-Krekola, Jaakko Särelä, Harri Valpola
2007	J	`jnl`	Blind separation of nonlinear mixtures by variational Bayesian learning. Digit. Signal Process. Antti Honkela, Harri Valpola, Alexander Ilin, Juha Karhunen
2007	J	`jnl`	Building Blocks for Variational Bayesian Learning of Latent Variable Models. J. Mach. Learn. Res. Tapani Raiko, Harri Valpola, Markus Harva, Juha Karhunen
2007	J	`jnl`	Compact Modeling of Data Using Independent Variable Group Analysis. IEEE Trans. Neural Networks Esa Alhoniemi, Antti Honkela, Krista Lagus, Santeri Jeremias Seppä, Paul Wagner, Harri Valpola
2006	J	`jnl`	Exploratory analysis of climate data using source separation methods. Neural Networks Alexander Ilin, Harri Valpola, Erkki Oja
2006	B	`conf`	Extraction of Components with Structured Variance. IJCNN Alexander Ilin, Harri Valpola, Erkki Oja
2006	—	`conf`	Separation of Nonlinear Image Mixtures by Denoising Source Separation. ICA Mariana S. C. Almeida, Harri Valpola, Jaakko Särelä
2005	A	`conf`	Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework. UAI Markus Harva, Tapani Raiko, Antti Honkela, Harri Valpola, Juha Karhunen
2005	J	`jnl`	Denoising Source Separation. J. Mach. Learn. Res. Jaakko Särelä, Harri Valpola
2005	—	`conf`	Development of Representations, Categories and Concepts - a Hypothesis. CIRA Harri Valpola
2005	—	`conf`	Frequency-Based Separation of Climate Signals. PKDD Alexander Ilin, Harri Valpola
2005	J	`jnl`	On the Effect of the Form of the Posterior Approximation in Variational Learning of ICA Models. Neural Process. Lett. Alexander Ilin, Harri Valpola
2005	B	`conf`	Semiblind source separation of climate data detects El Nino as the component with the highest interannual variability. IJCNN Alexander Ilin, Harri Valpola, Erkki Oja
2004	—	`conf`	Accurate, Fast and Stable Denoising Source Separation Algorithms. ICA Harri Valpola, Jaakko Särelä
2004	J	`jnl`	Hierarchical models of variance sources. Signal Process. Harri Valpola, Markus Harva, Juha Karhunen
2004	J	`jnl`	Nonlinear dynamical factor analysis for state change detection. IEEE Trans. Neural Networks Alexander Ilin, Harri Valpola, Erkki Oja
2004	—	`conf`	Unsupervised Variational Bayesian Learning of Nonlinear Models. NIPS Antti Honkela, Harri Valpola
2004	—	`conf`	Using Kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method. ICA Antti Honkela, Stefan Harmeling, Leo Lundqvist, Harri Valpola
2004	J	`jnl`	Variational learning and bits-back coding: an information-theoretic view to Bayesian learning. IEEE Trans. Neural Networks Antti Honkela, Harri Valpola
2003	J	`jnl`	Accelerating Cyclic Update Algorithms for Parameter Estimation by Pattern Searches. Neural Process. Lett. Antti Honkela, Harri Valpola, Juha Karhunen
2003	J	`jnl`	Independent component analysis for artefact separation in astrophysical images. Neural Networks Maria Funaro, Erkki Oja, Harri Valpola
2003	J	`jnl`	Nonlinear Blind Source Separation by Variational Bayesian Learning. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Harri Valpola, Erkki Oja, Alexander Ilin, Antti Honkela, Juha Karhunen
2002	J	`jnl`	An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models. Neural Comput. Harri Valpola, Juha Karhunen
2001	C	`conf`	Independent Variable Group Analysis. ICANN Krista Lagus, Esa Alhoniemi, Harri Valpola