M
Mauro Castelli
Researcher at Universidade Nova de Lisboa
Publications - 202
Citations - 3718
Mauro Castelli is an academic researcher from Universidade Nova de Lisboa. The author has contributed to research in topics: Genetic programming & Computer science. The author has an hindex of 24, co-authored 174 publications receiving 2520 citations. Previous affiliations of Mauro Castelli include University of Milan & University of Lisbon.
Papers
More filters
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
The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset
Ibrahem Kandel,Mauro Castelli +1 more
TL;DR: The results concluded that a higher batch size does not usually achieve high accuracy, and the learning rate and the optimizer used will have a significant impact as well.
Journal ArticleDOI
Better GP benchmarks: community survey results and proposals
David White,James McDermott,Mauro Castelli,Luca Manzoni,Brian W. Goldman,Gabriel Kronberger,Wojciech Jaśkowski,Una-May O'Reilly,Sean Luke +8 more
TL;DR: Community support is found for creating a “blacklist” of problems which are in common use but have important flaws, and whose use should therefore be discouraged, and a set of possible replacement problems are proposed.
Journal ArticleDOI
The impact of big data analytics on firms' high value business performance
TL;DR: The findings indicate that BDA capability along with organizational readiness and design factors facilitated better utilization of BDA in manufacturing decision making, and thus enhanced high value business performance.
Journal ArticleDOI
A survey of semantic methods in genetic programming
TL;DR: This survey analyzes and discusses the state of the art in the field, organizing the existing methods into different categories, and restricts itself to studies where semantics is intended as the set of output values of a program on the training data.