What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Erkki Oja mostly deals with Artificial intelligence, Independent component analysis, Algorithm, Artificial neural network and Pattern recognition.
Erkki Oja focuses mostly in the field of Artificial intelligence, narrowing it down to topics relating to Machine learning and, in certain cases, Parallel computing.
The Independent component analysis study combines topics in areas such as FastICA, Blind signal separation, Source separation, Magnetoencephalography and Generative model.
The concepts of his Algorithm study are interwoven with issues in Mathematical optimization, Non-negative matrix factorization, Principal component analysis and Parameter space.
His biological study spans a wide range of topics, including Subspace topology, Data mining and Feed forward.
Erkki Oja interconnects Histogram, Probabilistic logic and Prior probability in the investigation of issues within Pattern recognition.
His most cited work include:
- Independent Component Analysis (8216 citations)
- Independent component analysis: algorithms and applications (6221 citations)
- A fast fixed-point algorithm for independent component analysis (2981 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Pattern recognition, Artificial neural network, Independent component analysis and Algorithm.
His work carried out in the field of Artificial intelligence brings together such families of science as Machine learning and Computer vision.
His studies deal with areas such as Subspace topology, Speech recognition and Hebbian theory as well as Pattern recognition.
His Independent component analysis research integrates issues from FastICA, Blind signal separation, Signal processing, Nonlinear system and Principal component analysis.
His Blind signal separation research is multidisciplinary, incorporating elements of Latent variable, Source separation and Robustness.
He focuses mostly in the field of Algorithm, narrowing it down to matters related to Mathematical optimization and, in some cases, Applied mathematics.
He most often published in these fields:
- Artificial intelligence (58.90%)
- Pattern recognition (35.96%)
- Artificial neural network (22.26%)
What were the highlights of his more recent work (between 2009-2016)?
- Non-negative matrix factorization (6.85%)
- Artificial intelligence (58.90%)
- Cluster analysis (8.90%)
In recent papers he was focusing on the following fields of study:
Non-negative matrix factorization, Artificial intelligence, Cluster analysis, Algorithm and Nonnegative matrix are his primary areas of study.
His work carried out in the field of Artificial intelligence brings together such families of science as Machine learning, Data mining and Pattern recognition.
His research integrates issues of Speech recognition and Source separation in his study of Pattern recognition.
The various areas that Erkki Oja examines in his Cluster analysis study include Probabilistic latent semantic analysis, Maxima and minima, Mathematical optimization and Rank.
His Algorithm research incorporates elements of Matrix decomposition and Blind signal separation.
His Robustness study incorporates themes from Independent component analysis and FastICA.
Between 2009 and 2016, his most popular works were:
- Linear and Nonlinear Projective Nonnegative Matrix Factorization (169 citations)
- GPU-accelerated and parallelized ELM ensembles for large-scale regression (131 citations)
- Clustering by Nonnegative Matrix Factorization Using Graph Random Walk (66 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Erkki Oja spends much of his time researching Non-negative matrix factorization, Algorithm, Nonnegative matrix, Cluster analysis and Discrete mathematics.
In the field of Algorithm, his study on Least squares overlaps with subjects such as Numerical weather prediction.
His Nonnegative matrix research is multidisciplinary, incorporating perspectives in Kullback–Leibler divergence, Artificial intelligence, Graph partition, Norm and Applied mathematics.
His Artificial intelligence study frequently draws connections between adjacent fields such as Supercomputer.
His studies in Cluster analysis integrate themes in fields like Pattern recognition, Random walk and Rank.
His Pattern recognition study frequently draws connections to other fields, such as Column.
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.
