Harri Valpola

7.1k total citations · 1 hit paper
41 papers, 1.6k citations indexed

About

Harri Valpola is a scholar working on Signal Processing, Artificial Intelligence and Analytical Chemistry. According to data from OpenAlex, Harri Valpola has authored 41 papers receiving a total of 1.6k indexed citations (citations by other indexed papers that have themselves been cited), including 22 papers in Signal Processing, 20 papers in Artificial Intelligence and 10 papers in Analytical Chemistry. Recurrent topics in Harri Valpola's work include Blind Source Separation Techniques (21 papers), Neural Networks and Applications (15 papers) and Spectroscopy and Chemometric Analyses (10 papers). Harri Valpola is often cited by papers focused on Blind Source Separation Techniques (21 papers), Neural Networks and Applications (15 papers) and Spectroscopy and Chemometric Analyses (10 papers). Harri Valpola collaborates with scholars based in Finland, Russia and United States. Harri Valpola's co-authors include Juha Karhunen, Tapani Raiko, Yann LeCun, Antti Honkela, Jaakko Särelä, Erkki Oja, Alexander Ilin, Tommi Vatanen, А. А. Ильин and Timo Honkela and has published in prestigious journals such as Neural Computation, Neural Networks and Journal of Machine Learning Research.

In The Last Decade

Harri Valpola

38 papers receiving 1.4k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

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

2017 783 citations Harri Valpola et al. arXiv (Cornell University) profile →

Peers

Countries citing papers authored by Harri Valpola

Since Specialization

Citations

This map shows the geographic impact of Harri Valpola's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Harri Valpola with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Harri Valpola more than expected).

Fields of papers citing papers by Harri Valpola

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Harri Valpola. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Harri Valpola. The network helps show where Harri Valpola may publish in the future.

Co-authorship network of co-authors of Harri Valpola

This figure shows the co-authorship network connecting the top 25 collaborators of Harri Valpola. A scholar is included among the top collaborators of Harri Valpola based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Harri Valpola. Harri Valpola is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work	Indexed citations
1	Weight-averaged consistency targets improve semi-supervised deep learning results. 2017 ·arXiv (Cornell University) ·(unknown), Harri Valpola	38
2	Denoising autoencoder with modulated lateral connections learns invariant representations of natural images 2014 ·International Conference on Learning Representations ·Antti Rasmus, Tapani Raiko, Harri Valpola	1
3	Deep Learning Made Easier by Linear Transformations in Perceptrons 2012 ·International Conference on Artificial Intelligence and Statistics ·Tapani Raiko, Harri Valpola, Yann LeCun	87
4	Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention 2011 ·Advances in experimental medicine and biology ·Tapani Raiko, Harri Valpola	6
5	Building Blocks for Variational Bayesian Learning of Latent Variable Models 2007 ·Journal of Machine Learning Research ·Tapani Raiko, Harri Valpola, (unknown), Juha Karhunen	15
6	Exploratory analysis of climate data using source separation methods 2006 ·Neural Networks ·Alexander Ilin, Harri Valpola, Erkki Oja	17
7	Semiblind source separation of climate data detects El Nino as the component with the highest interannual variability 2006 ·Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. ·А. А. Ильин, Harri Valpola, Erkki Oja	6
8	Denoising Source Separation 2005 ·Journal of Machine Learning Research ·Jaakko Särelä, Harri Valpola	111
9	On the Effect of the Form of the Posterior Approximation in Variational Learning of ICA Models 2005 ·Neural Processing Letters ·Alexander Ilin, Harri Valpola	15
10	Behaviourally Meaningful Representations From Normalisation And Context-Guided Denoising 2004 ·CogPrints (University of Southampton) ·Harri Valpola	3
11	Unsupervised Variational Bayesian Learning of Nonlinear Models 2004 ·Neural Information Processing Systems ·Antti Honkela, Harri Valpola	31
12	Nonlinear Dynamical Factor Analysis for State Change Detection 2004 ·IEEE Transactions on Neural Networks ·А. А. Ильин, Harri Valpola, Erkki Oja	12
13	Variational Learning and Bits-Back Coding: An Information-Theoretic View to Bayesian Learning 2004 ·IEEE Transactions on Neural Networks ·Antti Honkela, Harri Valpola	33
14	Bayes Blocks Software Library 2003 ·Harri Valpola, Antti Honkela, (unknown), (unknown), Tapani Raiko, (unknown)	5
15	Nonlinear Independent Factor Analysis by Hierarchical Models 2003 ·Cancer Treatment and Research Communications ·Harri Valpola, (unknown), Juha Karhunen	16
16	Missing Values in Hierarchical Nonlinear Factor Analysis 2003 ·Tapani Raiko, Harri Valpola, (unknown), Juha Karhunen	6
17	Independent component analysis for artefact separation in astrophysical images 2003 ·Neural Networks ·(unknown), Erkki Oja, Harri Valpola	23
18	DETECTING PROCESS STATE CHANGES BY NONLINEAR BLIND SOURCE SEPARATION 2003 ·(unknown), Harri Valpola, Erkki Oja	9
19	Artefact Detection In Astrophysical Image Data Using Independent Component Analysis 2001 ·(unknown), Erkki Oja, Harri Valpola	1
20	Dynamical Factor Analysis Of Rhythmic Magnetoencephalographic Activity 2001 ·Jaakko Särelä, Harri Valpola, Ricardo Vigário, Erkki Oja	8

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact