Alejandro Dopico-Castro

I’m currently a PhD student working on Frugal AI at the University of A Coruña, in the Laboratory of Research and Development of Artificial Intelligence (LIDIA Group). My research focuses on developing resource-efficient learning systems, such as those explored in Continuous Learning, Federated Learning and Few-shot Learning.

Previously, I earned an MSc in Artificial Intelligence and a BSc in Computer Science. I also worked as a full-time researcher on the PILLAR-Robots project, where I developed intelligent systems for autonomous agents.

Right now, I’m working on my PhD thesis at LIDIA, focusing on green, frugal AI by designing learning algorithms that are both efficient and deployable in real-world settings.

I’m passionate about everything related to Artificial Intelligence and Deep Learning—from Computer Vision to Natural Language Processing. I’m also an enthusiastic hackathon participant, having competed in several events.

news

Jun 15, 2025	Breaking news: I finally have a personal website! ( still under construction)

selected publications

Efficient Single-Step Framework for Incremental Class Learning in Neural Networks

A. Dopico-Castro^*, Ó. Fontenla-Romero, B. Guijarro-Berdiñas, and A. Alonso-Betanzos

2025

Abs Bib Website

Incremental learning continues to present a significant challenge in deep learning, particularly in environments where resources are limited. While existing methods have been shown to achieve high levels of accuracy, they often require substantial computational resources and storage capacity. This work proposes CIFNet, an efficient approach to class incremental learning that matches comparable accuracy to state-of-the-art methods while significantly reducing training time and energy consumption through a single-step optimisation process. CIFNet incorporates a novel compressed buffer mechanism that stores condensed representations of previous data samples instead of full raw data, substantially reducing memory requirements. In contrast to conventional approaches that necessitate multiple iterations of weight optimisation, our method achieves optimal performance in a single training step, with no need for iterations, leading to a significant decrease in computational overhead. Experimental results on standard benchmark datasets have shown that our approach inherently mitigates catastrophic forgetting without the need for complex regularization schemes. CIFNet achieves accuracy comparable to current state-of-the-art approaches while significantly reducing training time and energy consumption. This work represents a step forward in making class incremental learning more accessible for resource-constrained environments while maintaining robust performance.
@mastersthesis{dopico2025efficient, title = {Efficient Single-Step Framework for Incremental Class Learning in Neural Networks}, author = {Dopico-Castro, A. and Fontenla-Romero, Ó. and Guijarro-Berdiñas, B. and Alonso-Betanzos, A.}, year = {2025}, school = {Universidade da Coruña}, type = {Master's Thesis}, }