K
Krzysztof Krawiec
Researcher at Poznań University of Technology
Publications - 166
Citations - 4188
Krzysztof Krawiec is an academic researcher from Poznań University of Technology. The author has contributed to research in topics: Genetic programming & Fitness function. The author has an hindex of 26, co-authored 164 publications receiving 3666 citations. Previous affiliations of Krzysztof Krawiec include University of California, Riverside & Massachusetts Institute of Technology.
Papers
More filters
Journal ArticleDOI
Segmenting Retinal Blood Vessels With Deep Neural Networks
TL;DR: A supervised segmentation technique that uses a deep neural network trained on a large sample of examples preprocessed with global contrast normalization, zero-phase whitening, and augmented using geometric transformations and gamma corrections, which significantly outperform the previous algorithms on the area under ROC curve measure.
Book ChapterDOI
Geometric semantic genetic programming
TL;DR: This work introduces a novel form of GP --- Geometric Semantic GP (GSGP) --- that searches directly the space of the underlying semantics of the programs, and allows for principled formal design of semantic search operators for different classes of problems.
Proceedings ArticleDOI
Genetic programming needs better benchmarks
James McDermott,David White,Sean Luke,Luca Manzoni,Mauro Castelli,Leonardo Vanneschi,Wojciech Jaskowski,Krzysztof Krawiec,Robin Harper,Kenneth de Jong,Una-May O'Reilly +10 more
TL;DR: This paper argues that the definition of standard benchmarks is an essential step in the maturation of the field and motivates the development of a benchmark suite and defines its goals.
Journal ArticleDOI
Rough set reduction of attributes and their domains for neural networks
TL;DR: Promising results let us claim that the rough set approach is a useful tool for preprocessing of data for neural networks.
Journal ArticleDOI
Genetic Programming-based Construction of Features for Machine Learning and Knowledge Discovery Tasks
TL;DR: The extended approach proposed in the paper proved to be able to outperform the standard approach on some benchmark problems on a statistically significant level and to show that classifiers induced using the representation enriched by the GP-constructed features provide better accuracy of classification on the test set.