- author = "Domagoj Jakobovic and Luca Manzoni and Luca Mariot and Stjepan Picek and Mauro Castelli",
- title = "CoInGP: Convolutional Inpainting with Genetic Programming",
- booktitle = "Proceedings of the 2021 Genetic and Evolutionary Computation Conference",
- year = "2021",
- editor = "Francisco Chicano and Alberto Tonda and Krzysztof Krawiec and Marde Helbig and Christopher W. Cleghorn and Dennis G. Wilson and Georgios Yannakakis and Luis Paquete and Gabriela Ochoa and Jaume Bacardit and Christian Gagne and Sanaz Mostaghim and Laetitia Jourdan and Oliver Schuetze and Petr Posik and Carlos Segura and Renato Tinos and Carlos Cotta and Malcolm Heywood and Mengjie Zhang and Leonardo Trujillo and Risto Miikkulainen and Bing Xue and Aneta Neumann and Richard Allmendinger and Fuyuki Ishikawa and Inmaculada Medina-Bulo and Frank Neumann and Andrew M. Sutton",
- pages = "795--803",
- address = "internet",
- series = "GECCO '21",
- month = jul # " 10-14",
- organisation = "SIGEVO",
- publisher = "Association for Computing Machinery",
- publisher_address = "New York, NY, USA",
- keywords = "genetic algorithms, genetic programming, Convolution, Supervised learning, Prediction, Images, Inpainting",
- isbn13 = "9781450383509",
-
URL = "
http://www.human-competitive.org/sites/default/files/mariot_0.txt",
-
URL = "
http://www.human-competitive.org/sites/default/files/jmmpc_coingp.pdf",
-
DOI = "
doi:10.1145/3449639.3459346",
- size = "9 pages",
- abstract = "We investigate the use of Genetic Programming (GP) as a convolutional predictor for missing pixels in images. The training phase is performed by sweeping a sliding window over an image, where the pixels on the border represent the inputs of a GP tree. The output of the tree is taken as the predicted value for the central pixel. We consider two topologies for the sliding window, namely the Moore and the Von Neumann neighbourhood. The best GP tree scoring the lowest prediction error over the training set is then used to predict the pixels in the test set. We experimentally assess our approach through two experiments. In the first one, we train a GP tree over a subset of 1000 complete images from the MNIST dataset. The results show that GP can learn the distribution of the pixels with respect to a simple baseline predictor, with no significant differences observed between the two neighborhoods. In the second experiment, we train a GP convolutional predictor on two degraded images, removing around 20 percent of their pixels. In this case, we observe that the Moore neighborhood works better, although the Von Neumann neighborhood allows for a larger training set.",
-
notes = "Entered 2021 HUMIES
University of Zagreb, Croatia
GECCO-2021 A Recombination of the 30th International Conference on Genetic Algorithms (ICGA) and the 26th Annual Genetic Programming Conference (GP)",
