Eduardo Paluzo-Hidalgo
epaluzo [at] uloyola.es
Social media:
Assistant Professor at Universidad Loyola
I finished my undergraduate studies in Mathematics in 2017 and obtained an MSc in Logic, Computation and Artificial Intelligence in 2018 at the University of Sevilla. Then, I began my research career with a young researcher position funded by the European Fund 2014-20 at the University of Sevilla and obtained my PhD in 2021 under the supervisión of Prof. Rocío González Díaz and Prof. Miguel Ángel Gutiérrez Naranjo. My thesis was devoted to topology-aware data reduction in the context of Machine Learning, as well as theoretical approaches from a Computational Topology perspective to the universal approximation capabilities of Artificial Neural Networks (ANNs) and their robustness against adversarial examples by defining a new flavour of ANN based on simplicial maps. From October 2019 to December 2024, I held a substitute teaching position at the Applied Math I department at the University of Sevilla. In the summer of 2023, I did research stays at Kyushu University and Kyoto University, both in Japan. You can check my research papers and other research activities below. They are mainly devoted to ANNs and Computational Topology. Since January of 2024, I have been an Assistant Professor at the Universidad Loyola (Campus Sevilla).
Publications
Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Trainable and explainable simplicial map neural networks, Information Sciences, Volume 667, 2024, 120474, ISSN 0020-0255, https://doi.org/10.1016/j.ins.2024.120474
D. Ali, A. Asaad, M. -J. Jimenez, V. Nanda, E. Paluzo-Hidalgo and M. Soriano-Trigueros, "A Survey of Vectorization Methods in Topological Data Analysis," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 12, pp. 14069-14080, Dec. 2023, doi: 10.1109/TPAMI.2023.3308391.
Gonzalez-Diaz, R., Gutiérrez-Naranjo, M.A. & Paluzo-Hidalgo, E. Topology-based representative datasets to reduce neural network training resources. Neural Comput & Applic 34, 14397–14413 (2022). https://doi.org/10.1007/s00521-022-07252-y
Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz, Guillermo Aguirre-Carrazana. Emotion recognition in talking-face videos using persistent entropy and neural networks[J]. Electronic Research Archive, 2022, 30(2): 644-660. doi: 10.3934/era.2022034
Boutry, N., Gonzalez-Diaz, R., Jimenez, MJ. et al. Strong Euler well-composedness. J Comb Optim 44, 3038–3055 (2022). https://doi.org/10.1007/s10878-021-00837-8
Paluzo-Hidalgo, E.; Gonzalez-Diaz, R.; Gutiérrez-Naranjo, M.A.; Heras, J. Optimizing the Simplicial-Map Neural Network Architecture. J. Imaging 2021, 7, 173. https://doi.org/10.3390/jimaging7090173
Paluzo-Hidalgo, E.; Gonzalez-Diaz, R.; Gutiérrez-Naranjo, M.A.; Heras, J. Simplicial-Map Neural Networks Robust to Adversarial Examples. Mathematics 2021, 9, 169. https://doi.org/10.3390/math9020169
Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Two-hidden-layer feed-forward networks are universal approximators: A constructive approach, Neural Networks, Volume 131, 2020, Pages 29-36, ISSN 0893-6080, https://doi.org/10.1016/j.neunet.2020.07.021.
Guillaume Damiand, Eduardo Paluzo-Hidalgo, Ryan Slechta, Rocio Gonzalez-Diaz, Approximating lower-star persistence via 2D combinatorial map simplification, Pattern Recognition Letters, Volume 131, 2020, Pages 314-321, ISSN 0167-8655, https://doi.org/10.1016/j.patrec.2020.01.018
Gonzalez-Diaz, R.; Mainar, E.; Paluzo-Hidalgo, E.; Rubio, B. Neural-Network-Based Curve Fitting Using Totally Positive Rational Bases. Mathematics 2020, 8, 2197. https://doi.org/10.3390/math8122197
Preprints
Application of the representative measure approach to assess the reliability of decision trees in dealing with unseen vehicle collision data J Perera-Lago, V Toscano-Durán, E Paluzo-Hidalgo, S Narteni, M Rucco preprint arXiv:2404.09541
SIMAP: A simplicial-map layer for neural networks R Gonzalez-Diaz, MA Gutiérrez-Naranjo, E Paluzo-Hidalgo arXiv preprint arXiv:2403.15083
An In-Depth Analysis of Data Reduction Methods for Sustainable Deep Learning V Toscano-Durán, J Perera-Lago, E Paluzo-Hidalgo, R Gonzalez-Diaz, MA Gutiérrez-Naranjo, M Rucco arXiv preprint arXiv:2403.15150
A Topological Approach to Measuring Training Data Quality Á Torras-Casas, E Paluzo-Hidalgo, R Gonzalez-Diaz arXiv preprint arXiv:2306.02411
Summary and Distance between Sets of Texts based on Topological Data Analysis E Paluzo-Hidalgo, R Gonzalez-Diaz, MA Gutiérrez-Naranjo arXiv preprint arXiv:1912.09253
Research stays
Kyushu University, with Professor Yuichi Ike (1 month), Summer 2023
Kyoto University, with Professor Yasuaki Hiraoka (1 month), Summer 2023
Conference proceedings
Algebraically-informed deep networks for associative evolution algebras Víctor Manuel Gómez Sousa, Desamparados Fernández-Ternero, Juan Núñez-Valdés and Eduardo Paluzo-Hidalgo XX Spanish Meeting on Computational Geometry
The metric-aware kernel-width choice for LIME Aurelio Barrera-Vicent, Eduardo Paluzo-Hidalgo, Miguel A Gutiérrez-Naranjo 1st World Conference on eXplainable Artificial Intelligence (xAI-2023)
Boutry, N., Gonzalez-Diaz, R., Jimenez, MJ., Paluzo-Hildago, E. (2020). Euler Well-Composedness. In: Lukić, T., Barneva, R., Brimkov, V., Čomić, L., Sladoje, N. (eds) Combinatorial Image Analysis. IWCIA 2020. Lecture Notes in Computer Science(), vol 12148. Springer, Cham. https://doi.org/10.1007/978-3-030-51002-2_1
Gonzalez-Diaz, R., Paluzo-Hidalgo, E., Quesada, J.F. (2019). Towards Emotion Recognition: A Persistent Entropy Application. In: Marfil, R., Calderón, M., Díaz del Río, F., Real, P., Bandera, A. (eds) Computational Topology in Image Context. CTIC 2019. Lecture Notes in Computer Science(), vol 11382. Springer, Cham. https://doi.org/10.1007/978-3-030-10828-1_8
Rocio Gonzalez-Diaz, Eduardo Paluzo-Hidalgo, Miguel A. Gutiérrez-Naranjo, Representative datasets for neural networks, Electronic Notes in Discrete Mathematics, Volume 68, 2018, Pages 89-94, ISSN 1571-0653, https://doi.org/10.1016/j.endm.2018.06.016
Conferences & seminars
Jul, 2023. TDA week, Kyoto University. Poster title: An Introduction to Simplicial-map Neural Networks Trainability and Explainability.
Jul, 2023. 産業数理統計セミナー Kyushu University seminar. Talk title: Computational Topology for Machine Learning practitioners
Jun, 2022. Algebraic Topology Meeting Conference, Oxford University. Poster title: Simplicial-map neural networks.
May, 2022. First International Workshop on Smart Computing Applications, Koya University (online). Talk title: A Computational Topology Approach to emotion recognition.
Jan, 2020. Rubio de Francia seminar, University of Zaragona, Spain. Talk title: Universal approximation theorem and simplicial approximation theorem, a constructive approximation.
Sept, 2019. Seminar, L2F Research Department, EPFL, Lausanne. Talk title: Topology and Neural Networks
May, 2019. Geometric Data Analysis Conference, University of Chicago. Poster title: Reducing the size of datasets.
Jan, 2019. Computational Topology in Image Context, University of Málaga. Talk title: Towards emotion recognition: a persistent entropy application.
Oct, 2018. XXV Encuentro de Topología, Institut d’Estudis Catalans, Barcelona. Poster title:Topología y redes neuronales artificiales. Dragon Applied Topology conference, Swansea University. Talk title: Neural Networks and Topology.
Sept, 2018. Dragon Applied Topology conference, Swansea University. Talk title: Neural networks and Topology.
Jun,2018. Discrete Mathematics Days, University of Sevilla. Talk title: Representative datasets for neural networks.
Participation in current and past research projects
REliable & eXplAinable Swarm Intelligence for People with Reduced mObility (REXASI-PRO) (GRANT AGREEMENT NO.101070028)
Topología Computacional para el ahorro de energía y la optimización de métodos de aprendizaje profundo para alcanzar soluciones verdes de Inteligencia Artificial (TED2021-129438B-I00)
Advances in topics on computational topology and its relationship with neural networks (P20_01145)
Advances in Topología Computacional y Aplicaciones (PID2019-107339GB-I00)
Collaborators
In no particular order.
Aras Asaad
Dashti Ali
J F Quesada
Juan Núñez Valdés
Guillermo Aguirre Carrazana
Víctor Manuel Gómez Sousa
Matteo Rucco
Javier Perera-Lago
Víctor Toscano-Durán
Sara Narteni
Universidad Loyola Andalucía, Av. de las Universidades, 2, 41704 Dos Hermanas, Sevilla