Special Issue:

Machine Learning Applications in Metabolomics Analysis

RESEARCH TOPIC:  AI and Multi-Omics for Rare diseases: Challenges, Advances and Perspectives. Volume III

Curso on-line: Deep Learning: Introducción

Este curso brinda una introducción práctica al aprendizaje profundo (Deep Learning), una técnica de la inteligencia artificial que ha revolucionado la escena tecnológica para posicionarse de la mano del Big Data como un elemento central en la estrategia de innovación de las principales empresas del sector. Se introducirán primero los conceptos generales necesarios sobre reconocimiento de patrones, redes neuronales, aprendizaje supervisado, etc., que permitan entender el funcionamiento y la utilidad de los sistemas de reconocimiento y predicción de patrones basados en aprendizaje profundo, para poder luego realizar una implementación práctica de los mismos, primero utilizando ejemplos clásicos y posteriormente poder realizar un proyecto individual.

Inscripciones: aquí

                                             

Dr.  L. Franco  grew up in Argentina, completing his master and doctoral degrees in the theoretical physics group at FaMAF, University of Córdoba. He obtained a PhD under the mentorship of Dr. Sergio A. Cannas, studying the generalization properties of feedforward neural networks. He did a postdoctoral fellowship for two years at SISSA, Trieste-Italy in Prof. Alessandro Treves laboratory. From 2002 to 2005 he worked as a post-doctoral fellow with Dr. Edmund Rolls at the University of Oxford, United Kingdom. He joined Málaga University as a Ramón y Cajal fellow in 2005. In June 2010 he became Associate Professor, to then got the Full Professorship post in July 2021 in the Department of Computer Science, Malaga University  School of  Engineering in Informatics . He belongs to the Computational Intelligence and Bioinformatics group (ICB), that is also integrated within IBIMA(Institute for Biomedical Research Málaga).

L. Franco does research on the areas of Machine Learning, Artificial Intelligence, Deep Learning, Large Language Models, and application to Pattern Recognition and Data Mining mainly to  biomedical and environmental problems. He is senior member of the IEEE, belonging to the Computational Intelligence Society, and associate editor for the Journal IEEE Transactions on Neural Networks and Learning Systems. He regularly lectures undergraduates courses on "Deep Learning" and "Automata Theory and Formal Languages", and master courses on  "Artificial Neural Networks" and "New technologies for Marketing". 

Artificial Intelligence, Machine learning: One of the most remarkable properties of artificial neural networks is their ability to generalize to novel inputs. This predictive capability is fundamental to many tasks such as image recognition, disease progression modeling, text generation, and other applications that today have a profound societal impact, as Artificial Intelligence continues to transform our lives. In the early stages of my career, I designed novel neural network architectures and analyzed their computational capabilities. Several studies led us to propose a  complexity of Boolean functions related to the generalization ability achievable when such functions are implemented in neural networks. In collaboration with Dr. J. M. Jerez (Málaga), Dr. M. Anthony (LSE), and Dr. S.A. Cannas (Córdoba), we analyzed the properties of this measure and explored interesting extensions and connections with physics. Subsequently, we developed constructive learning algorithms that enable the automatic design of near-optimal neural architectures, alleviating the need to manually select a suitable architecture for a given problem. These constructive methods also facilitate knowledge (rule) extraction, helping to interpret how a network solves a task. Together with David Elizondo (Leicester), I edited a book on Constructive Neural Networks published by Springer in the Computational Intelligence Series. More recently, we developed two new constructive algorithms—DASG and C-Mantec. In collaboration with Francisco Ortega, we implemented the C-Mantec algorithm and classical back-propagation on FPGA hardware, enabling very fast execution and applications in sensor networks for monitoring tasks. We have also implemented a deep version of the back-propagation algorithm on FPGA, thereby entering the field of Deep Learning [A44].. Deep Learning extends traditional neural networks by incorporating multiple hidden layers, and its recent results have been extraordinary, achieving superhuman performance in several domains. One major limitation in applying Deep Learning is the scarcity of sufficiently large training datasets. To address this issue, during the PhD thesis of J. Moreno-Barea we developed data augmentation techniques to improve predictive performance [A52], and successfully applied them to metabolomics data [A54].

LLM (Large Language Models):  Understanding and generating text is a complex task at which humans excel and that posed major challenges for computational models for decades. Since the emergence of Large Language Models around 2018, dramatic advances have been achieved. Within the ICB group, we apply LLMs to tasks such as named-entity recognition, transfer learning, and model comparison [A53][A57]. Our work involves a wide range of models—including Mistral, LLaMA, BERT, and ChatGPT—and techniques such as fine-tuning, retrieval-augmented generation (RAG), and agent-based systems. A major focus is the analysis of Electronic Health Records, particularly in oncology, forming a research line closely related to our work in biomedicine.

Biomedicine, Cancer Research: For many years, the ICB group has applied data mining and Artificial Intelligence techniques to medical prognosis. In collaboration with Dr. J. M. Jerez (Málaga), E. Alba (Hospital Clínico de Málaga), and other colleagues, we have organized scientific activities and published numerous journal articles [A13] [A27] [A41] [A42]. As a result of this long-standing collaboration, we also developed the software system Galén for managing oncology units, which has been implemented at the Hospital Clínico de Málaga [B12][A43].

Neuroscience: I have also conducted extensive research in Computational Neuroscience, focusing on neuronal coding—how information is represented and transmitted in the brain. This work involved analyzing neural recordings using information-theoretic methods, developing new techniques, and performing simulations to test competing hypotheses. We studied information coding under natural conditions to determine whether it is dominated by firing rates or whether correlations between neurons play a significant role. Additional work examined correlated responses and quantified the sparseness of representations in cells of the inferior temporal visual cortex [A20]. Other studies analyzed how information is encoded in fMRI voxel activity during decision-making tasks, comparing these findings with neurophysiological data   [A7] [A8] [A9] [A24]. More recently, my work in this area has focused on exploring the connections between Neuroscience and Deep Learning approaches.

   

COPYRIGHT NOTICE: The documents distributed here have been provided as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Books: 

[B3]  Computational Science – ICCS 2024. Franco, L., de Mulatier, C., Paszynski, M.,  Krzhizhanovskaya, V., Dongarra, J., Sloot, P.M.A. 24th International Conference, Malaga, Spain, July 2–4, 2024, Proceedings, Parts I-VII. [Book]

[B2] Constructive neural networks. L.Franco, D. Elizondo and J.M. Jerez (Eds.), Springer (2010). Series: Studies in Computational   Intelligence, Vol. 258, ISBN:  978-3-642-04511-0. [Springer site]  [More Info]

[B1]    Escenario de Emisiones de Gases de Efecto Invernadero en la Ciudad de Málaga. I. Molina Conde, J.M.  Jerez Aragonés, L. Franco, E.M. Sánchez Teba and P. Marín Cots. Ediciones del Ayuntamiento de Málaga, España. ISBN: 978-84-692-0913-4. (2009).

Journals :

[A57] J. Montes-Torres, F.J. Moreno-Barea, L.Franco, N.Ribelles, E. Alba, & J.M. Jerez (2026). Oncology data extraction with large language models from real-world breast cancer electronic health records in Spanish. Machine Learning with Applications, 100837.  [pdf]

[A56] F. Ortega-Zamorano, J.M. Jerez, J. Rodríguez-Alabarce, K. Goreishi & L. Franco  (2025). Efficient thermal comfort estimation employing the C-Mantec constructive neural network model. Soft Computing, 29, pp.4673--4684. [pdf]

[A55] S. Bottini, F. Emmert-Streib & L. Franco  (2024). Editorial: AI and Multi-Omics for Rare diseases: Challenges, Advances and Perspectives. Frontiers in Molecular Biosciences, 11:1392943. [pdf]

[A54] F.J. Moreno-Barea, L. Franco, D.  Elizondo  & M. Grootveld. Application of data augmentation techniques towards metabolomics. Computers in Biology and Medicine, 148, 105916 (2022).  [pdf]

[A53] N. Ribelles, J.M. Jerez, et al. Machine learning and natural language processing (NLP) approach to predict early progression to first-line treatment in real-world hormone receptor-positive (HR+)/HER2-negative advanced breast cancer patients. European Journal of Cancer, 144, pp. 224-231 (2021). [pdf]

[A52] F.J. Moreno-Barea, J.M. Jerez, and L. Franco. Improving Classification Accuracy Using Data Augmentation on Small Data Sets. Experts Systems with Applications, 161:113696 (2020). [pdf]

[A51] G. López-García, J.M. Jerez, L. Franco, and F.J.Veredas. Transfer learning with convolutional neural networks for cancer survival prediction using gene-expression data. PLOS ONE, 15(3):e0230536 (2020). [pdf]

[A50] I. Gómez, H. Mesa, F. Ortega-Zamorano, J.M. Jerez and L. Franco. Improving learning and generalization capabilities of the C-Mantec constructive neural network algorithm. Neural Computing and Applications,  32, pp. 8955–8963 (2020). [pdf]

[A49] J. González-Enrique,  I.J. Turias,  J.J. Ruiz-Aguilar; J.A.  Moscoso-López, J.M. Jerez and L. Franco. Estimation of NO2 concentration values in a monitoring sensor network using a fusion approach. Fresenius Environmental Bulletin, 28, pp. 681-686 (2019). [pdf]

[A48] J. González-Enrique,  I.J. Turias,  J.J. Ruiz-Aguilar; J.A. Moscoso-López, and L. Franco. Spatial and meteorological relevance in NO2 estimations. A case study in the bay of Algeciras. Stochastic Environmental Research and Risk Assessment, 33, pp. 801-815 (2019).  [pdf]

[A47] D. Urda, F. Aragón,  R. Bautista, L. Franco, F. Veredas, G. Claros, and J.M. Jerez. BLASSO: integration of biological knowledge into a regularized linear model. BMC Systems Biology, 12 (Suppl 5):94  (2018). [pdf]

[A46] F. Ortega-Zamorano, J.M. Jerez, G.E. Juárez,  and L. Franco. FPGA implementation of neurocomputational models: comparison between standard Back-Propagation and C-Mantec constructive algorithm. Neural Processing Letters,  46, pp. 899-914 (2017). [pdf]

[A45] C. Rodríguez-Rivero, J. Pucheta, S. Laboret,  V. Sauchelli,  A.D. Orjuela-Cañon, and L. Franco.  Noisy Chaotic time series forecast approximated by combining Renyi's entropy with Energy associated to series method: application to rainfall series. IEEE Latin American Transactions, 15, pp. 1318-1325. (2017). [pdf]

[A44] F. Ortega-Zamorano, J.M. Jerez, I. Gómez,  and L. Franco. Layer Multiplexing FPGA implementation for Deep Back-Propagation Learning. Integrated Computer Aided-Engineering, 24, pp.171-185 (2017). [pdf]

[A43] J. Montes-Torres, J.L. Subirats, N. Ribelles, D. Urda, L. Franco, E. Alba and J.M. Jerez. Advanced Online Survival Analysis Tool for Predictive Modelling in Clinical Data Science. PLOS ONE, 11(8): e0161135 (2016). [pdf]

[A42] I. Gómez, N. Ribelles, L. Franco, E. Alba, and J.M. Jerez. Supervised discretization can discover risk groups in cancer survival analysis . Computer Methods and Programs in Biomedicine, 136, pp 11-19 (2016). [pdf]

[A41] F. Ortega-Zamorano, M. Montemurro, S.A. Cannas, J.M. Jerez,  and L. Franco. FPGA Hardware Acceleration of Monte Carlo Simulations for the Ising Model. IEEE Transactions on Parallel and Distributed Systems, 27, pp. 2618 - 2627 (2016). [pdf]

[A40] F. Ortega-Zamorano, J.M. Jerez, D. Urda, R.M. Luque-Baena and L. Franco. Efficient Implementation of the Backpropagation Algorithm in FPGAs and Microcontrollers. IEEE Transactions on Neural Networks and Learning Systems, 27, pp. 1840-1850 (2016). [pdf]

[A39] I. Gómez, S.A. Cannas, O. Osenda, J.M. Jerez, and L. Franco. The Generalization Complexity Measure for Continuous Input Data. The Scientific World Journal, ID:815156 (2014). [pdf]

[A38] F. Ortega-Zamorano, J.M. Jerez, J.L. Subirats, I. Molina, and L. Franco. Smart sensor/actuator node reprogramming in changing environments using a neural network model. Engineering Applications of Artificial Intelligence, 30, pp. 179-188 (2014). [pdf]

[A37] R. Luque-Baena, D. Urda, G. Claros, L. Franco and J.M. Jerez. Robust gene signatures from microarray data using genetic algorithms enriched with biological pathway keywords. Journal of Biomedical Informatics, 49, pp. 32-44 (2014). [pdf] 

[A36] F. Ortega-Zamorano, J.M. Jerez,  and  L. Franco. FPGA implementation of the C-Mantec Constructive Neural Network Algorithm. IEEE Transactions on Industrial Informatics, 10, pp. 1154-1161 (2014). [pdf]

[A35] R. Luque Baena, D. Urda, J.L. Subirats, L. Franco, and J.M. Jerez. Application of Genetic Algorithms and Constructive Neural Networks for the Analysis of Microarray Cancer Data. Theoretical Biology and Medical Modelling, 11, S1(S7) (2014). [pdf]

[A34] N. Ribelles, L., Pérez-Villa, J.M. Jerez, B. Pajares, L. Vicioso, B. Jiménez, V. de Luque, L. Franco, E. Gallego, A. Márquez, M. Alvarez, A. Sánchez-Muñoz, L. Pérez-Rivas, and E. Alba. Pattern of recurrence of early breast cancer is different according to intrinsic subtype and proliferation index. Breast Cancer Research, 15, R98 (2013). [pdf]  

[A33] D. Urda,  N. Ribelles, J.L. Subirats, L. Franco, and E. Alba. Addressing critical issues in the development of an Oncology Information System. International Journal of Medical Informatics, 82, pp. 398-407 (2013). [pdf]

[A32] L.G. Pérez-Rivas, J.M.  Jerez, J.M., C.E. Fernández-de Sousa, V. de Luque, C.  Quero, B.  Pajares, L. Franco, A. Sanchez-Muñoz, N. Ribelles and  E. Alba.  Serum protein levels following surgery in breast cancer patients: A protein microarray approach. International Journal of Oncology,41, pp. 2200-2206 (2012). [pdf]

[A31] D. Urda, J.L. Subirats, P.J. García-Laencina, L. Franco, J.L. Sancho-Gómez, and J.M. Jerez. WIMP: Web server tool for missing data imputation. Computer Methods and Programs in Biomedicine, 108, pp.1247-1254 (2012). [pdf]

[A30] D. Urda, E. Cañete, J.L. Subirats, L. Franco, L. Llopis, and J.M. Jerez. Energy-efficient Reprogramming in WSN using Constructive Neural Networks. International Journal of Innovative Computing, Information and Control, 8, pp. 7561-7578 (2012). [pdf]

[A29] J.L. Subirats,  L. Franco and J.M. Jerez. C-Mantec: a novel constructive neural network algorithm incorporating competition between neurons. Neural Networks, 26, pp 130-140 (2012). [pdf]

[A28] J.P. Neirotti and L. Franco. Computational capabilities of multilayer committee machines. Journal of Physics A: Mathematical & Theoretical, 43, 445103 (2010). [pdf]

[A27] J.M. Jerez, I. Molina, P.J. García-Laencina, E. Alba, N. Ribelles, M. Martín and L. Franco. Missing Data Imputation Using Statistical and Machine Learning Methods in a Real Breast Cancer Problem. Artificial Intelligence in Medicine, 50, pp.105-115 (2010). [pdf]

[A26] J.L Subirats, J.M. Jerez, I. Gómez & L. Franco (2010). Multiclass pattern recognition extension for the new C-Mantec constructive neural network algorithm. Cognitive Computation, 2, pp. 285-290 (2010). [pdf]

[A25] I. Gómez,  L. Franco and J.M. Jerez. Neural Network Architecture Selection: Can function complexity help?. Neural Processing Letters, 30, pp. 71-87 (2009).  [pdf]

[A24] E.T. Rolls, F. Grabenhorst  and L. Franco. Prediction of Subjective Affective State from Brain Activations . Journal of Neurophysiology, 101, pp.1294-1308 (2009). [pdf]

[A23]  J.L. Subirats, J.M. Jerez and L. Franco. A New Decomposition Algorithm for Threshold Synthesis and Generalization of Boolean Functions. IEEE Transactions on Circuits and Systems I, 55, pp. 3188-3196 (2008). [pdf]

[A22]  L. Franco, J.L. Subirats and J.M. Jerez. MaxSet: An Algorithm for Finding a Good Approximation for the Largest Linearly Separable Set. Lecture Notes in Computer Science, 4668, pp. 648-656  (2007).  [pdf]

[A21]  L. Franco, J.L. Subirats, I. Molina, E. Alba and J.M. Jerez. Early breast cancer prognosis prediction and rule extraction  using a new constructive neural network algorithm. Lecture Notes in Computer Science, 4507, pp. 1004-1011  (2007). [pdf]

[A20]  L. Franco, E.T. Rolls, N.C. Aggelopoulos and J.M. Jerez. Neuronal selectivity, population sparseness, and  ergodicity in the inferior temporal visual cortex. Biological Cybernetics, 96, pp. 547-560  (2007). [pdf]

[A19] E.T. Rolls, L. Franco, N.C. Aggelopoulos and J.M. Jerez. Information in the first spike, the order of spikes, and the number of spikes provided by neurons in the inferior temporal visual cortex. Vision Research, 46, pp. 4193-4205 (2006). [pdf]

[A18] J.L. Subirats, I. Gómez, J.M. Jerez and L. Franco. Optimal Synthesis of Boolean Functions by Threshold Functions. Lecture Notes in Computer Science, 4131, pp. 983-992 (2006). [pdf]

[A17] I. Gómez, L. Franco, J.L. Subirats and J.M. Jerez. Neural Networks Architecture Selection: Size Depends on Function Complexity. Lecture Notes in Computer Science, 4131, pp. 122-129 (2006). [pdf]

[A16] L. Franco. Generalization ability of  Boolean functions implemented in feedforward neural networks. Neurocomputing, 70, pp. 351-361 (2006). [pdf]

[A15] L. Franco and M. Anthony. The influence of oppositely classified examples on the generalization complexity of Boolean functions. IEEE Transactions on Neural Networks,  17, pp. 578--590 (2006). [pdf]

[A14] V.G. Hadjianastassiou, L. Franco, J.M. Jerez, I.E. Evangelou,  D.R. Goldhill, P.P. Tekkis, L.J. Hands.  Optimal prediction of mortality  after abdominal aortic aneurism  repair with statistical models. Journal of Vascular Surgery,  43,  pp. 467--473 (2006). [pdf]

[A13] J. Jerez, L. Franco, E. Alba,  A. Llombart-Cussac, A. Lluch, N. Ribelles, B. Munárriz and M. Martín. Improvement of Breast Cancer Relapse Prediction in High Risk Intervals Using Artificial Neural Networks. Breast Cancer Research and Treatment, 94,  pp. 265--272 (2005). [pdf]

[A12] E.T. Rolls,  L. Franco and S.M. Stringer. The perirhinal cortex and long term familiarity memory. Quarterly Journal of Experimental Psychology, Section B, 58, pp. 234--245 (2005). [pdf]

[A11] E.T. Rolls,  J-Z. Xiang and L. Franco. Object, space, and object-space representations in the human hippocampus. Journal of Neurophysiology, 94, pp. 833--844 (2005). [pdf]

[A10] L. Franco, J.M. Jerez, and J.M. Bravo-Montoya. Role of Function Complexity and Network Size in the Generalization Ability of Feedforward Networks.  Lecture Notes in Computer Science, 3512, pp. 1--8 (2005). [pdf]

[A9] N.C. Aggelopoulos,  L. Franco and E.T. Rolls. Object perception in natural scenes: encoding by inferior temporal cortex simultaneously recorded neurons. Journal of Neurophysiology,  93,  pp. 1342--1357 (2005).[pdf]

[A8] L. Franco, E.T. Rolls, A. Treves and N.C. Aggelopoulos. The use of decoding to analyze the contribution to the information of the correlations between the firing of simultaneously recorded neurons. Experimental Brain Research,  155 pp. 370--384, (2004). [pdf]     

[A7] E.T. Rolls, N.C. Aggelopoulos, L. Franco, and A. Treves. Information encoding in the inferior temporal visual cortex: contributions of the firing rates and the correlations between the firing of neurons. Biological Cybernetics,  90, pp. 19--32  (2004). [pdf]

[A6] L. Franco and S.A. Cannas. Non-glassy ground state in a long-range antiferromagnetic frustrated model in the hypercubic cell. Physica A, 332, pp. 337--348 (2004). [pdf]

[A5] J.M. Jerez, L. Franco and  I. Molina. CBA generated receptive fields implemented in a Facial expression recognition task. Lecture Notes in Computer Science,  2686,  pp. 734--741 (2003). [pdf]

[A4] E.T. Rolls, L. Franco, N.C. Aggelopoulos, and S. Reece. An information theoretic approach to the contributions of the firing rates and correlations between the firing of neurons. Journal of Neurophysiology, 89, pp. 2810--2822  (2003). [pdf]

[A3] L. Franco and S.A. Cannas. Generalization Properties of Modular Networks: Implementing the Parity Function. IEEE Transactions on Neural Networks, 12, pp. 1306--1313 (2001). [pdf]

[A2] L. Franco and S.A. Cannas. Generalization and Selection of Examples in Feed-Forward Neural Networks. Neural Computation, 12, pp. 2405-- 2426 (2000). [pdf]

[A1] L. Franco and S.A. Cannas. Solving Arithmetic Problems Using Feed-Forward Neural Networks. Neurocomputing, 18, pp. 61--79 (1998). [pdf]
  

Proceedings, Lecture Notes, Book chapters & other publications  

[B45] C. Rodriguez-Rivero, J. Pucheta, P. Otaño, C. Salas et al.,  Flood occurrence prediction using Monte Carlo methods and machine learning for mitigating climate impact in Northwestern Argentina. 12th International Conference on Soft Computing & Machine Intelligence (ISCMI),  pp. 98-102, (2025). doi: 10.1109/ISCMI67495.2025.11358627. IEEE Press. [pdf] [bibtex] 

[B44] F.J. Moreno-Barea,  Jerez, J.M., Franco, L.  Data augmentation to improve molecular subtype prognosis prediction in breast cancer. International Conference on Computational Science. Lecture Notes in Computer Science, 6, pp.19-27 (2024). doi: 10.1007/978-3-031-08757-8_3

[B43] Alhoseinifakhraei, S., Franco, L. Semantic Web usage in the tourism industry in Andalusia, Spain. International Conference on Tourism, Management and Hospitality, 1(1):38-49  (2024).

[B42] F.J. Moreno-Barea,  Jerez, J.M., Franco, L.  Data Augmentation Meta-Classifier Scheme  for imbalanced data sets.  Proceedings IEEE SSCI’22, Symposium Series on Computational Intelligence, Singapur. pp. 1392-1399, doi: 10.1109/SSCI51031.2022.10022209. (2022).

[B41] F.J. Moreno-Barea,  Jerez, J.M., Franco, L. GAN-Based Data Augmentation for Prediction Improvement Using Gene Expression Data in Cancer. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13352. Springer, Cham.  (2022). https://doi.org/10.1007/978-3-031-08757-8_3

[B40] F.J. Moreno-Barea,  Franco, L., Elizondo, D., Grootveld, M.  Data Augmentation Techniques to Improve Metabolomic Analysis in Niemann-Pick Type C Disease. (2022). In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13352. Springer,  (2022). https://doi.org/10.1007/978-3-031-08757-8_8

[B39] G. E. Juárez, F. D. Menéndez, C. H. Lafuente, J. Pérez, L. Franco and C. R. Rivero, Analysis and simulation of social behavior during the COVID-19 pandemic in Argentina, using intelligent agents. 2022 IEEE World Engineering Education Conference (EDUNINE), (2022), pp. 1-6. IEEE xplore.

[B38] C, Rodriguez-Rivero, J. Puchet, D. Patiño, P. Otaño,  L. Franco, & G. Juárez. Short-Term Rainfall Forecasting with E-LSTM Recurrent Neural Networks Using Small Datasets. Lecture Notes in Computer Science, 12465, pp. 258-270. (2020). Proceedings ICIC'2020, Bari, Italia.

[B37] G. García-López, José M. Jerez Aragonés,  L. Franco, & F. Veredas. A transfer-learning approach to feature extraction from cancer transcriptomes with deep autoencoders. Lecture Notes in Computer Science, 11506, pp. 912-924. (2019). Proceedings IWANN'2019, Gran Canaria, España.

[B36] D. Urda-Muñoz,  L. Franco, I. Turias, F. Veredas. Addition of pathway-based information to improve prediction in transcriptomics. Lecture Notes in Bioinformatics, 11466, pp. 200-208 (2019). Proceedings of the 2019 IWBBIO, Granada, España.

[B35] F.J. Moreno-Barea, F. Strazzera, J.M. Jerez, D. Urda, & L. Franco. Forward Noise Adjustment Scheme for Data Augmentation. Proceedings of the 2018 Symposium Series on Computational Intelligence, Bengaluru, India. (2018). [pdf]

[B34] A.L. Fraga, M.G. Gramajo, F. Trejo, S. García, G. Juárez,  & L. Franco. SIMNET: Simulation-based exercises for Computer Network Curriculum through Gamification and Augmented Reality. Lecture Notes in Networks and Systems (Smart Industry & Smart Education), 47, pp. 627-635. (2019). ISBN: 978-3-319-95677-0.[pdf]

[B33]  D. Urda, L. Franco and J.M. Jerez. Classification of high dimensional data using LASSO ensembles. Proceedings IEEE SSCI'17, Symposium Series on Computational Intelligence, Honolulu, Hawaii, U.S.A. (2017). [pdf]

[B32]  C. Rodriguez Rivero, Y. Tupac, J. Pucheta, G. Juarez, L. Franco and P. Otaño. Time-series Prediction with BEMCA Approach: application to short rainfall series. Proceedings IEEE LA-CCI'17, Latin American Conference on Computational Intelligence, Cuzco, Perú. (2017).[pdf]

[B31] D. Urda, J. Montes-Torres, F. Moreno, L.  Franco & J.M. Jerez.  Deep learning to analyze RNA-Seq gene expression data. Lecture Notes in Computer Science, 10306, pp. 50-59. (2017).

[B30] J.L. Subirats, H. Mesa, F. Ortega, G.E. Juárez, J.M. Jerez, I. Turias,  & L. Franco. Solving Scheduling Problems with Genetic Algorithms using a Priority Encoding Scheme. Lecture Notes in Computer Science, 10305, pp. 52-61. (2017).

[B29] I.J. Turias, J.M. Jerez, L. Franco, H. Mesa, J.J. Ruiz Aguilar, J.A. Moscoso & M.J. Jiménez.  Prediction of carbon monoxide (co) atmospheric pollution concentrations using meteorological variables.  Proceeedings Air Pollution Conference 2017. WIT Press Conference Papers. 25-27 April (2017).

[B28]  D. Urda, R. Luque, N. Sánchez, L. Franco and J.M. Jerez. Machine learning models to search relevant genetic signatures in clinical context. Proceedings IJCNN, International Joint Conference on Neural Networks, Anchorage, Alaska,  pp.1649-1656. (2017).

[B27]  D. Urda, F. Aragón, L. Franco, F. Veredas and J.M. Jerez. L1-regularization model enriched with biological knowledge. Proceedings IWBBIO, Granada, (2017).

[B26]  J. Rodriguez-Alabarce, F. Ortega-Zamorano,  J.M. Jerez, K. Goreishi,  and L. Franco.  Thermal Comfort Estimation using a Neurocomputational Model. Proceedings IEEE Latin American Conference on Computational Intelligence,  (2016). [Best Paper Award]
 
[B25]  C. Rodríguez-Rivero, J. Pucheta, A. Orjuela-Cañon and L. Franco. Noisy Chaotic time series forecast approximated by combining Renyi entropy with Energy associated to series method: application to rainfall series. Proc. IEEE Latin American Conference on Computational Intelligence, (2016).

[B24]  F. Ortega-Zamorano,  J.M. Jerez, I. Gómez,  and L. Franco. Deep Neural Network Architecture Implementation on FPGAs Using a Layer Multiplexing Scheme. Springer Series on Advances in Intelligent Systems and Computing, 474, pp. 79-86, (2016). ISBN: 978-3-319-40162-1

[B23] F. Ortega-Zamorano,  J.M. Jerez, G. Juárez, and L. Franco. FPGA implementation comparison between C-Mantec and Back-Propagation Neural Network Algorithms. Lecture Notes in Computer Science, 9095, pp. 197-208. (2015).

[B22]  F. Ortega-Zamorano,  J.M. Jerez, G. Juárez, J.O. Pérez and L. Franco. High Precision FPGA Implementation of Neural Network Activation functions. Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI'2014), pp. 55-60, (2014). ISBN: 978-1-4799-4486-6

[B21]  D. Urda, S. Chambers, I. Jarman, P. Lisboa, L. Franco and J.M. Jerez. Use of q-values to improve a genetic algorithm to identify robust gene signatures. Lecture Notes in Computer Science, 8623, pp. 199-206, (2015).

[B20]  F. Ortega-Zamorano, J.L. Subirats, J.M. Jerez, I. Molina and L. Franco. Implementation of the C-Mantec Neural Network Constructive Algorithm in an Arduino Uno Microcontroller. Lecture Notes in Computer Science, 7902, pp. 80-87, (2013). ISBN: 978-3-642-38678-7

[B19]  J.L. Subirats, R.M. Luque, D. Urda, F. Ortega, J.M. Jerez and L. Franco. Committee C-Mantec: A Probabilistic Constructive Neural Network. Lecture Notes in Computer Science, 7902, pp. 339-346, (2013). ISBN: 978-3-642-38678-7

[B18]  D. Urda, R.M. Luque, M.J.  Jiménez, I. Turias, L. Franco and J. M. Jerez. A constructive neural network to predict pitting corrosion status of stainless steel. Lecture Notes in Computer Science, 7902, pp. 88-95, (2013). ISBN: 978-3-642-38678-7

[B17]  R.M. Luque-Baena, D. Urda, J.L. Subirats, L. Franco, and J.M. Jerez. Analysis of Cancer Microarray Data using Constructive Neural Networks and Genetic Algorithms. Proceedings of the IWBBIO, International Work-Conference on Bioinformatics and Biomedical Engineering, pp. 55-64 (2013). ISBN: 978-84-15814-13-9

[B16]  J.J. Carneros, J.M. Jerez, I. Gómez & L. Franco. Data Discretization Using the Extreme Learning Machine Neural Network. Lecture  Notes in   Computer Science, 7666, pp. 281-288. Proceedings of the ICONIP 2012 Conference, Qatar, November 2012. [pdf]

[B15]  Y. Couce,  L. Franco, D. Urda, J.L. Subirats  and J.M. Jerez. Hybrid (Generalization-Correlation) method for feature selection in high dimensional DNA microarray prediction problems. Lecture Notes in Artificial Intelligence, 6692, pp. 202-209. Proceedings of the IWANN 2011 conference, Torremolinos, Spain, June 8-10, (2011). ISBN: 978-3-642-21498-1 [pdf]

[B14]  D. Urda, J.L. Subirats, L. Franco,  and J.M. Jerez. Constructive neural networks to predict breast cancer outcome by using gene expression profiles. Lecture Notes in Artificial Intelligence, 6096, pp. 317-326. Proceedings of the IEA-AIE, Córdoba, Spain, June 1-3, (2010). ISBN: 978-3-642-13021-2. [pdf]

[B13]  I. Gómez, L. Franco, J.M. Jerez & J.L. Subirats. Extension of the generalization complexity measure to real valued input data sets. Lecture Notes in Computer Science, 6063, pp. 86-94. Proceedings of the ISNN'2010, Shanghai, China, June 6-9, (2010). ISBN: 978-3-642-13277-3. [pdf]

[B12] N. Ribelles, J.M. Jerez, D. Urda, J.L. Subirats, A. Marquez,  C. Quero, E. Torres, L. Franco & E. Alba. Galén: Sistema de Información para la gestión y coordinación de procesos en un servicio de Oncología. RevistaeSalud, 6 (21) (2010).  [pdf]

[B11]  J.L. Subirats, L. Franco, I. Molina and J.M. Jerez. Active learning using a constructive neural network algorithm. Lecture Notes in Computer Science, 5164, pp. 803-811. Proceedings of the International Conference in Artificial Neural Networks (ICANN), Praga, República Checa, 3-6 September. (2008). [pdf]

[B10] J.L. Subirats, L. Franco, I. Gómez and J.M. Jerez. Computational capabilities of feedforward neural networks: the role of the output function. Proceedings of the XII CAEPIA'07, Salamanca, Spain, vol. II, pp. 231-238. ISBN: 978-84-611-8848-2. November 12-16 (2007).  [pdf]

[B9] L. Franco, J.L. Subirats, M. Anthony and J.M. Jerez. A New Constructive Approach for the Set of Linearly Separable Functions. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN'06 - WCCI'06), Vancouver, Canada, pp. 9541-9546. ISBN: 0-7803-9490-9. July 16-21 (2006). [pdf]

[B8] J.M. Jerez, I. Molina, L. Franco, and  J.L. Subirats. Missing Data Imputation in Breast Cancer Prognosis. Proceedings of the IASTED International Multiconference in Biomedical Engineering, Innsbruck, Austria, pp. 323-328. ISBN: 0-88986-576-0. February 15-17 (2006). [pdf]

[B7] L. Franco,  J.M. Jerez  and E. Alba. Artificial neural networks and prognosis in medicine. Survival analysis in breast cancer patients.  Proceedings of the European Symposium on Artificial Neural Networks (ESANN'05), Bruges, Belgium, pp. 91-102. ISBN 2-930307-05-6. April 27-29 (2005). [pdf]

[B6] L. Franco and M. Anthony. On a Generalization complexity measure for Boolean functions. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN'04), Budapest, Hungary, pp. 973-978. ISBN 0-7803-8359. July 25-28 (2004). [pdf]

[B5] L. Franco and J.M. Jerez. Modularity: a Natural Way of Improving Generalization. Proceedings of the 3rd WSES International Conference on Neural Networks, Interlaken, Switzerland.  ISBN: 960-8052-48-3. February 11-15. (2002). [abstract]

[B4] L. Franco and A. Treves. A Neural Network Face Expression Recognition System using Unsupervised Local Processing.  Proceedings of the Second International Symposium on Image and Signal Processing and Analysis (ISPA 01), Croatia, pp. 628-632. ISBN: 953-96769-4-0.  June 19-21. (2001). [pdf]

[B3] L. Franco, A. Montagnini  and A. Treves. A modular Neural Network for Facial Expression Recognition. Proceedings of the International Conference of Cognitive Modeling (ICCM). Halifax, VA. July 26–28 (2001).

[B2] L. Franco and S.A. Cannas. Improving Network Generalization through Selection of Examples. Proceedings of IV Argentinian Meeting on Computer Science (CACIC 98). Neuquén. Argentina, pp. 373-382. October 26-31 (1998). [pdf]

[B1] L. Franco and S. A. Cannas. Energy landscape and learning on a neural network for the sum problem. Proceedings of the Second International Workshop on (semi) numerical techniques in polynomial equation solving TERA 97, Trabajos de Matemática serie B, FaMAF, Universidad Nacional de Cordoba, Argentina, pp. 28-33. September 4-6 (1997). [pdf]

Teaching related publications & projects   

[C2]  J.M. Jerez, D. Bueno,  I.A. Molina, D. Urda, and L. Franco. Improving Motivation in Learning Programming Skills for Engineering Students.  International Journal of Engineering Education, 28, pp. 202-208. (2012). [pdf]

[C1] M.C. Alonso, J. Béjar, A. Cabeza, A.G. De la Torre, L. Franco, E. García-Rosado, Y. Vida. Elaboración de unidades didácticas con herramientas docentes Interdisciplinares para la adaptación de asignaturas al EEES. IV Jornadas de Innovación Educativa y Enseñanza Virtual en la Universidad de Málaga. (2010). [pdf]

Grants supporting our research activities:

[G8] PID2024-155334OB-I00, Ministerio de Ciencia, Innovación y Universidades, Proyectos de Generación de Conocimientos. Modelos de Lenguaje (LLM) y de Generación Aumentada por Recuperación (RAG) para la Extracción de Información Objetiva de Textos Oncológicos en Español.  202.250€€. IPs: Francisco Veredas y Leonardo Franco.

[G7] UMA20-FEDERJA-045, Junta de Andalucía, Proyectos FEDER, AIomics: Aplicaciones de Técnicas de Inteligencia Artificial a Conjuntos de Datos Ómicos para la Predicción en Cáncer. 57.182€€. IPs: Leonardo Franco y Miguel Atencia.

[G6] TIN2017-88728-C2-1-R Avances en el diseño y adaptación de algoritmos de aprendizaje profundo para su aplicación a problemas en las areas de biomedicina y contaminación atmosférica. 94.501€ €. IPs: José M. Jerez Aragonés y Leonardo Franco.

[G5]  TIN2014-58516-c2-1-R, MICIIN:  Diseño de estrategias adaptativas en sensores inteligentes y aplicación a la predicción de contaminantes atmosféricos en entornos locales. 83.611€€.  IP: Leonardo Franco - José M. Jerez Aragonés.

[G4]  P10-TIC-5770, Junta de Andalucía: Modelo Neurocomputacional de confort térmico en espacios públicos urbanos. 136.080€ € IP: Leonardo Franco.

[G3]  TIN2008-04985, MICIIN : Nuevas estrategias en el diseño de sistemas neurocomputacionales. Aplicación al procesamiento de información en oncología. 89.540€€.  IP: Leonardo Franco.

[G2]  A/6030/06 y A/12805/07, AECI: Inferencia Bayesiana mediante redes neuronales y su aplicación a biomedicina. 42.500€ €. IP: Leonardo Franco.

[G1]  Proyecto Ramón y Cajal, MICIIN, Financiación adicional: Redes Neuronales: Estudio de la complejidad de generalización y aplicaciones a la predicción de recidiva de cáncer de mama. 12.000€€. IP: Leonardo Franco.

[GE6] PID2020-116898RB-I00. MICIIN, Inteligencia Artificial para Procesamiento de Lenguaje Natural de Texto Clínico en Español para Análisis de Real-World-Data (Text2RWD).  109.989€ €.  IPs: J.M. Jerez Aragonés / F.J. Veredas Navarro.

[GE6] UMA-CEIATECH-01. Intelligent Data Analysis and Machine Learning in an oncology information system. Junta de Andalucía, Andalucía Tech RIS3. 31.307,50€ €. IP: J.M. Jerez Aragonés.

[GE4] TIN2010-16556, MICIIN, Sistemas inteligentes bioinspirados aplicados a medicina personalizada, 92.000€ €. IP: José M. Jerez Aragonés. (10/01/2011 ---31/12/2013).

[GE3] P08-TIC-04026, Junta de Andalucía, Proyectos de Investigación de Excelencia: Diseño de métodos constructivos en sistemas neurocomputacionales y aplicación a minería de datos en Oncología,  225.635,68€ €. IP: José M. Jerez Aragonés. (12/01/2008 ---11/01/2012)

[GE2]  TIN2005-02984 , MICIIN: :  Diseño de un sistema neurocomputacional para predicción de recidiva en cáncer de mama operable . Estudio de la relación complejidad-generalización en redes neuronales artificiales. 87.000€€.  IP: José M. Jerez Aragonés

[GE1]  P06-TIC-01615, Junta de Andalucía: Sistemas de teledetección Inteligentes. 190.536€€. IP: José Muñoz Perez

Thesis:

[T2] L. Franco. Learning and Generalization Properties of Feed-Forward Neural Networks. Ph.D. Thesis. Biblioteca FaMAF. Universidad Nacional de Córdoba. Argentina. (2000). [pdf]  (In Spanish)

[T1] L. Franco. Study of Learning Properties of Feed-Forward Neural Networks using Generalized Simulated Annealing algorithms. Thesis submitted within the requirements to obtain the degree of Licenciado in Physics. FaMAF Library. Argentina. (1995). [abstract]

Some Recent & Future Presentations: