Juha Karhunen focuses on Artificial intelligence, Independent component analysis, Unsupervised learning, Blind signal separation and Artificial neural network. His work deals with themes such as Algorithm, Machine learning and Pattern recognition, which intersect with Artificial intelligence. The concepts of his Pattern recognition study are interwoven with issues in Infomax, Theoretical computer science and Neural algorithms.
His Independent component analysis study frequently draws parallels with other fields, such as Prior probability. His studies in Prior probability integrate themes in fields like Probabilistic logic, FastICA, Neural coding and Negentropy. His Hebbian theory and Learning rule study in the realm of Artificial neural network interacts with subjects such as Generalized Hebbian Algorithm.
Juha Karhunen spends much of his time researching Artificial intelligence, Pattern recognition, Independent component analysis, Artificial neural network and Algorithm. His research on Artificial intelligence often connects related areas such as Machine learning. The concepts of his Pattern recognition study are interwoven with issues in Subspace topology, Missing data and Probability distribution.
His work carried out in the field of Independent component analysis brings together such families of science as Image processing, Canonical correlation, Singular value decomposition and Blind signal separation. His Artificial neural network study combines topics from a wide range of disciplines, such as Remote sensing and Radiance. His study on Algorithm also encompasses disciplines like
Artificial intelligence, Jet, Machine learning, Tokamak and Divertor are his primary areas of study. His research in Artificial intelligence intersects with topics in Data mining, Malware, Computer vision and Pattern recognition. Juha Karhunen interconnects Domain and Representation in the investigation of issues within Pattern recognition.
His Machine learning research incorporates elements of Inference, Bayesian inference and Complex dynamics. Juha Karhunen has researched Tokamak in several fields, including Nuclear engineering and Computational physics. His Artificial neural network research includes elements of Unsupervised learning, Meteorology and Feature learning.
Juha Karhunen focuses on Artificial intelligence, Machine learning, Pattern recognition, Nuclear engineering and Divertor. His Artificial intelligence study integrates concerns from other disciplines, such as Series and Malware. He has included themes like Complex dynamics, Context, Inference and Bayesian inference in his Machine learning study.
His research on Pattern recognition focuses in particular on Canonical correlation. His Nuclear engineering research integrates issues from Electron cyclotron resonance, ASDEX Upgrade and Plasma surface interaction. His biological study spans a wide range of topics, including Robot, Extension, Blind signal separation and Generalized canonical correlation.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
Independent Component Analysis
Aapo Hyvarinen;Juha Karhunen;Erkki Oja.
On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
Erkki Oja;Juha Karhunen.
Journal of Mathematical Analysis and Applications (1985)
A class of neural networks for independent component analysis
J. Karhunen;E. Oja;L. Wang;R. Vigario.
IEEE Transactions on Neural Networks (1997)
Representation and separation of signals using nonlinear PCA type learning
Juha Karhunen;Jyrki Joutsensalo.
Neural Networks (1994)
Generalizations of principal component analysis, optimization problems, and neural networks
Juha Karhunen;Jyrki Joutsensalo.
Neural Networks (1995)
Advances in Nonlinear Blind Source Separation
Christian Jutten;Juha Karhunen.
Nonlinear Blind Source Separation by Self-Organizing Maps
P. Pajunen;A. Hyvärinen;J. Karhunen.
Neural approaches to independent component analysis and source separation.
the european symposium on artificial neural networks (1996)
An unsupervised ensemble learning method for nonlinear dynamic state-space models
Harri Valpola;Juha Karhunen.
Neural Computation (2002)
Applications of neural blind separation to signal and image processing
J. Karhunen;A. Hyvarinen;R. Vigario;J. Hurri.
international conference on acoustics, speech, and signal processing (1997)
Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: