What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
His primary scientific interests are in Artificial intelligence, Bregman divergence, Combinatorics, Exponential family and Kullback–Leibler divergence. His work carried out in the field of Artificial intelligence brings together such families of science as Machine learning, Computer vision and Pattern recognition. Frank Nielsen works mostly in the field of Bregman divergence, limiting it down to topics relating to Weighted Voronoi diagram and, in certain cases, Bowyer–Watson algorithm and Computational geometry, as a part of the same area of interest.
The Combinatorics study combines topics in areas such as Centroid, Divergence, Applied mathematics, Euclidean geometry and Geodesic. His research integrates issues of Entropy, Class, Affine connection and Probability distribution in his study of Exponential family. His studies deal with areas such as Algorithm, Triangle inequality and Mathematical analysis, Piecewise as well as Kullback–Leibler divergence.
His most cited work include:
- Statistical region merging (647 citations)
- On weighting clustering (209 citations)
- DeepBach: a steerable model for bach chorales generation (148 citations)
What are the main themes of his work throughout his whole career to date?
Frank Nielsen focuses on Artificial intelligence, Cluster analysis, Combinatorics, Exponential family and Computer vision. His study looks at the relationship between Artificial intelligence and topics such as Pattern recognition, which overlap with Classification rule. His Cluster analysis research is multidisciplinary, incorporating perspectives in Algorithm, Data mining and Series.
His Combinatorics research incorporates elements of Set, Voronoi diagram, Bregman divergence, Computational geometry and Geodesic. The various areas that Frank Nielsen examines in his Bregman divergence study include Kullback–Leibler divergence, Mathematical analysis and Convex function. His work deals with themes such as Mixture model, Probability distribution and Pure mathematics, which intersect with Exponential family.
He most often published in these fields:
- Artificial intelligence (32.69%)
- Cluster analysis (18.41%)
- Combinatorics (15.11%)
What were the highlights of his more recent work (between 2016-2021)?
- Divergence (10.71%)
- Cluster analysis (18.41%)
- Information geometry (9.07%)
In recent papers he was focusing on the following fields of study:
His main research concerns Divergence, Cluster analysis, Information geometry, Applied mathematics and Combinatorics. His Divergence research includes themes of Kullback–Leibler divergence, Bregman divergence, Parametric family, Limit and Cauchy distribution. His Bregman divergence research focuses on Parametric statistics and how it connects with Algorithm.
His Cluster analysis study combines topics in areas such as Data mining, Time complexity, Dynamic programming, Multi-objective optimization and Optimization problem. Frank Nielsen has included themes like Space and Bhattacharyya distance in his Combinatorics study. Frank Nielsen focuses mostly in the field of Invariant, narrowing it down to matters related to Artificial intelligence and, in some cases, Geodesic.
Between 2016 and 2021, his most popular works were:
- DeepBach: a steerable model for bach chorales generation (148 citations)
- On the Jensen-Shannon Symmetrization of Distances Relying on Abstract Means. (32 citations)
- A review of two decades of correlations, hierarchies, networks and clustering in financial markets (32 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His primary areas of study are Divergence, Information geometry, Pure mathematics, Exponential family and Bregman divergence. His Divergence study which covers Cauchy distribution that intersects with Parametric family, Jensen–Shannon divergence, Hyperbolic geometry, Voronoi diagram and Delaunay triangulation. His Bregman divergence study integrates concerns from other disciplines, such as Kullback–Leibler divergence and Convex function.
His Kullback–Leibler divergence study combines topics from a wide range of disciplines, such as Mixture model, Mathematical analysis and Applied mathematics. The subject of his Curse of dimensionality research is within the realm of Artificial intelligence. His Artificial intelligence study incorporates themes from Unary operation and Natural language processing.
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.
