Advanced Machine Learning & Deep Learning

Research on advanced Machine Learning (ML) and Deep Learning (DL) has been at the forefront of artificial intelligence, paving the way for groundbreaking applications and transformative technologies. As computational power and data availability continue to grow exponentially, researchers have been able to push the boundaries of traditional machine learning techniques and delve into the complexities of deep learning architectures. These cutting-edge studies focus on improving model performance, interpretability, and generalization and addressing challenges like overfitting, non-conventional tasks and adversarial attacks. Moreover, advancements in neural network architectures, such as transformers, have revolutionized learning and computer vision tasks, enabling machines to understand any data and generate human-like text and images. As the research community delves deeper into this field, it opens up possibilities for autonomous systems, personalized medicine, smart cities, and enhanced human-computer interactions, promising a future where AI augments human capabilities and revolutionizes numerous industries.

Main current DaSCI research lines:

  • Advanced Machine Learning: Advancing machine learning techniques to handle unconventional data inputs, predictive models with prior knowledge for reliable and fair decisions, emphasizing efficient Big Data processing, exploring hybridizations with soft computing, aiming to revolutionize the field and focus on AutoML for non-conventional learning challenges. 
  • Deep Learning in Computer Vision: Our research focuses on computer vision, exploring diffusion-based generative models for facial aging and leveraging Vision Transformers for semi-supervised learning to enhance computer vision applications in diverse industrial contexts. 
  • Deep Learning and Symbolic AI: Progressing in Artificial Intelligence through theoretical contributions and combining deep learning with symbolic AI, exploring graph neural networks for constraint satisfaction and social network analysis, and using neural logic machines for automatic planning, bridging symbolic and sub-symbolic AI techniques.

Related Researchers:

Letra:

  Name Email Area Cat.
Aguirre Molina, Eugenio eaguirre@degqTj0Dhcsai.ugr.es
Bello García, Marilyn mbgarciauW3tNSLd4prU@ugr.es
Benítez Sánchez, José Manuel J.M.Benitez@decsaGNN0Il_z8Zei.ugr.es
Carmona del Jesus, Cristóbal J. ccarmona@uj8Erh4lnaen.es
Charte Ojeda, Francisco fcharte@FmCpq8n9oujaen.es
Fernandez Olivares, Juan faro@d6pMrHPLL9xEecsai.ugr.es
García Martínez, Carlos cgarcia@u3.s0GJ6YVco.es
García Silvente, Miguel m.garcia-silvente@decsai.ug3zfGenlLr.es
González Muñoz, Antonio A.Gonzalez@decsai.ugr.Q@H1AJpes Data Science and Big Data Area PhD
Górriz Sáez, Juan Manuel gorriz@ugr.1M4_@eEhPBfxes PhD
Lastra Leidinger, Miguel mlastral@ugr.em5H8TqMYes
Luna Ariza, Jose María jmlunaTZuIVIGY@uco.es
Martínez del Río, Francisco fmartin@ujae9z3hFaBYqG.Hn.es
Moyano Murillo, Jose María jmoyano@uc5iOfe1GAvs6vo.es
Ortíz García, Andrés aortiz@ic.uma.aXrCM01Wx2_es
Pérez Godoy, María Dolores lperez@uj5zmKV_zLSOeaen.es
Ramírez Pérez de Inestrosa, Javier javierrp@ug1iHEZWr.es
Ramírez Quesada, Aurora aramirez23Gah_t9T@uco.es
Rivera Rivas, Antonio Jesús arivera@ujaeQmcS3w3syn.es
Rodríguez Díaz, Francisco Javier fjrodriguez@decsai.ugrPUhKpZc_A.es
Rómero Salguero, José Raúl jrromero@uc1LB3PZrtPla2o.es