2017-Present: PhD student, Intelligent Systems Group (UPV/EHU)
2015-2016: Masters degree in Computer Engineering and Intelligent Systems (UPV/EHU).
2010-2015: Computer Science Degree (UPV/EHU).
U. Garciarena, A. Mendiburu and R. Santana. Towards Automatic Construction of Multi-Network Models for Heterogeneous Multi-Task Learning. ACM Transactions on Knowledge Discovery from Data. Vol. 15, Numer 2. Article number 33. 2021
U. Garciarena, A. Mendiburu, and R. Santana . EvoFlow: A Python library for evolving deep neural network architectures in tensorflow. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020, pp. 2288-2295. Canberra, Australia. IEEE Press.
U. Garciarena, A. Mendiburu and R. Santana. Analysis of the transferability and robustness of GANs evolved for Pareto set approximations. Neural Networks. Vol. 132. Pp. 281-296. 2020
U. Garciarena, A. Mendiburu, and R. Santana . Envisioning the Benefits of Back-Drive in Evolutionary Algorithms. Proceedings of the 2020 Congress on Evolutionary Computation (CEC-2020). Glasgow, Scotland. IEEE Press.
U. Garciarena, A. Mendiburu, and R. Santana . Automatic Structural Search for Multi-task Learning VALPs. OLA2020 CCIS Springer proceedings. Cádiz, Spain.
U. Garciarena, A. Mendiburu, and R. Santana . Towards automatic construction of multi-network models for heterogeneous multi-task learning. arXiv e-print (arXiv:1903.09171v1). 2019.
U. Garciarena, R. Santana, and A. Mendiburu . Evolved GANs for generating Pareto set approximations. Proceedings of the 2018 Genetic and Evolutionary Conference (GECCO-2018). Kyoto, Japan. P. 434-441.
U. Garciarena, A. Mendiburu, and R. Santana . Variational autoencoder for learning and exploiting latent representations in search distributions. Proceedings of the 2018 Genetic and Evolutionary Conference (GECCO-2018). Kyoto, Japan. P. 849-856.
U. Garciarena, R. Santana, and A. Mendiburu . Analysis of the complexity of the automatic pipeline generation problem. Proceedings of the 2018 Congress on Evolutionary Computation (CEC-2018). Rio de Janeiro, Brazil. IEEE Press. P. 1841-1841.
U. Garciarena, A. Mendiburu, and R. Santana . Towards a more efficient representation of imputation operators in TPOT. arXiv e-print (arXiv:1801.04407v1). 2018.
U. Garciarena, R. Santana, and A. Mendiburu . Evolving imputation strategies for missing data in classification problems with TPOT. arXiv e-print (arXiv:1706.01120v2). 2017.
U. Garciarena, and R. Santana. An extensive analysis of the interaction between missing data types, imputation methods, and supervised classifiers. Expert Systems and Applications. Vol. 89. Pp. 52-65. 2017
U. Garciarena. An investigation of imputation methods for discrete databases and multi-variate time series.(End of Masters Job, 2016)
U. Garciarena, and R. Santana Evolutionary optimization of compiler flag selection by learning and exploiting flags interactions.. Workshop on the Repair and Optimisation of Software using Computational Search (Genetic Improvement - 2016). Companion proceedings of the 2016 Genetic and Evolutionary Conference (GECCO-2016), Denver, CO., USA. Pp. 1159-1166. 2016.
U. Garciarena. Prototipo para la integración de datos públicos. (End of Degree Work, 2015)
Unai Garciarena received his bachelor degree in computer science in 2015, before obtaining his masters degree in computer engineering and intelligent systems, in 2016, both in the University of the Basque Country (UPV/EHU). He joined ISG in 2017 as a PhD student. His principal research interests are data preprocessing, supervised classification, and optimization.