Harri Valpola

7.1k citations
41 papers · 1.6k indexed · 1 hit paper · h-index 18

Harri Valpola

38 papers receiving 1.4k citations

Hit Papers

Mean teachers are better role models: Weight-averaged con...7832017202620202023250500750

Peers

Harri Valpola
Comparison fields: 5 of 120
  • Signal Processing 447
  • Computer Vision and Pattern Recognition 667
  • Artificial Intelligence 929
  • Analytical Chemistry 182
  • Cognitive Neuroscience 140
Replace Kap Luk Chan with:
Kap Luk Chan Singapore
Douglas E. Zongker United States
Konstantinos Koutroumbas Greece
Tao Xiong United States
Ghulum Bakiri Bahrain
Pascal Lamblin Canada
Francesco Masulli Italy
Mikel Luján United Kingdom
Elżbieta Pękalska Netherlands
K. Torkkola United States
Harri Valpola relative to Kap Luk Chan Singapore Kap Luk Chan's profile →
Citations per field
00.5×4.4×
Kap Luk Chan · 1×
Citations per year

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

The 17 scholars most cited alongside Harri Valpola, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Harri Valpola Line = papers co-authored together Harri Valpola links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown
#Work
1
Weight-averaged consistency targets improve semi-supervised deep learning results.
201738
2
Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
20141
3
Deep Learning Made Easier by Linear Transformations in Perceptrons
201287
4 20116
5
Building Blocks for Variational Bayesian Learning of Latent Variable Models
200715
6 200617
7 20066
8
Denoising Source Separation
2005111
9 200515
10
Behaviourally Meaningful Representations From Normalisation And Context-Guided Denoising
20043
11
Unsupervised Variational Bayesian Learning of Nonlinear Models
200431
12 200412
13 200433
14
Bayes Blocks Software Library
20035
15 200316
16
Missing Values in Hierarchical Nonlinear Factor Analysis
20036
17 200323
18
DETECTING PROCESS STATE CHANGES BY NONLINEAR BLIND SOURCE SEPARATION
20039
19
Artefact Detection In Astrophysical Image Data Using Independent Component Analysis
20011
20
Dynamical Factor Analysis Of Rhythmic Magnetoencephalographic Activity
20018

About Harri Valpola

Harri Valpola is a scholar working on Signal Processing, Analytical Chemistry and Artificial Intelligence, having authored 41 papers that have together received 1.6k indexed citations. Recurring topics across this work include Blind Source Separation Techniques (21 papers), Neural Networks and Applications (15 papers), Spectroscopy and Chemometric Analyses (10 papers), Fault Detection and Control Systems (6 papers), Advanced Neural Network Applications (3 papers), Climate variability and models (3 papers), Image and Signal Denoising Methods (2 papers) and Neural dynamics and brain function (2 papers). The work is most often cited by research in Signal Processing (447 citations), Computer Vision and Pattern Recognition (667 citations) and Artificial Intelligence (929 citations). Harri Valpola has collaborated with scholars based in Finland, Russia and United States. Frequent 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.

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

Rankless by CCL
2026