Tenemos el agrado de invitarles a nuestra próxima conferencia virtual organizada por el Centro Latinoamericano de Estudios en Informática (CLEI).
En esta ocasión, contaremos con la destacada presencia del Dr. Manuel Castillo-Cara, profesor e investigador de la Universidad Nacional de Educación a Distancia (UNED, España).
Detalles del evento:
- Tema: Improving Deep Learning on Tabular Data by Exploiting Synthetic Images
- Exponente: Dr. Manuel Castillo-Cara (UNED, España)
- Fecha: 3 de noviembre de 2026
- Hora: 13:00 – 14:00 (GMT-3)
- Plataforma: Zoom
Enlace de conexión:
Unirse a la sala virtual de Zoom
Abstract
Despite the breakthroughs of Deep Learning in computer vision and natural language processing, tabular data (which constitutes more than 80% of real-world corporate and scientific datasets) remains dominated by decision-tree-based algorithms due to the lack of inherent spatial relationships among variables.
This keynote address introduces a paradigm shift based on converting tabular observations into two-dimensional synthetic images to unlock the full potential of vision architectures. Throughout the session, the TINTOlib ecosystem will be presented, analyzing the principal spatial generation methods in the literature (supervised and unsupervised, as well as parametric approaches such as TINTO, REFINED, and IGTD).
Furthermore, the presentation will address advanced modeling through Convolutional Neural Networks (CNN), Vision Transformers (ViT), and prominently, Hybrid Neural Networks (HyNN) that fuse vision and tabular branches (CNN+MLP and ViT+MLP). Drawing on real-world use cases (e.g. indoor localization using Massive MIMO technology) and recent benchmarks, it will demonstrate how these hybrid architectures not only match or outperform classical baselines, but also act as learning stabilizers and regularizers. Finally, the latest developments in Explainable AI (XAI) tailored to this domain (such as PermGrad, Grad-CAM, and hybrid CNN–KAN models) will be examined, providing the means to audit and interpret the visual patterns extracted by models from transformed tabular data.
Bio
Manuel Castillo-Cara, Ph.D., is an Assistant Professor in the Department of Artificial Intelligence at Universidad Nacional de Educación a Distancia (UNED, Spain), accredited as an Associate Professor (Profesor Titular de Universidad) by ANECA and recognized with the R3 Certificate by the Spanish State Research Agency. Formerly a María Zambrano postdoctoral fellow at Universidad Politécnica de Madrid (UPM), his research focuses on multimodal artificial intelligence, with a specialized emphasis on the conversion of tabular data into synthetic images, hybrid neural networks (HyNN), and Explainable AI (XAI). He is the lead author of the TINTO mapping algorithm and the creator of the open-source library TINTOlib (with around 100,000 downloads). Backed by more than 30 publications in high-impact JCR journals (such as Information Fusion, IEEE Internet of Things Journal, and Knowledge-Based Systems), he has served as Principal Investigator on multiple competitive R&D
