Dr Julio Hurtado
I am an Innovation Research Associate (InRA) at CAMaCS and an International Collaborator with the Centro Nacional de Inteligencia Artificial in Chile (CENIA).
I did my PhD in Computer Science at the Pontificia Universidad Católica de Chile, specifically at the Laboratorio de Inteligencia Artificial (Artificial Intelligence Laboratory). Afterwards, I worked as a Research Associate at the Pervasive IA Lab (PAILAB) at the University of Pisa.
My main research focus is on Continual Learning, which aims to provide deep learning models with the ability to continually learn new knowledge without forgetting or interfering with previously learned weights. I am driven by learning representations more suitable for Continual Learning, encouraging generalisation and robustness in the model. My central hypothesis is that encouraging models to accumulate reusable and robust knowledge will help reduce forgetting by minimising the need to change previously learned weights.
Related topics to the previous idea are Out-Of-Distribution generalisation, Open-World learning, robustness and learning disentangled representations.
Before and during my PhD, I worked as a Data Scientist on a few projects, applying machine learning techniques to real-world problems and transferring research findings into real applications using NLP and Computer Vision models.
I worked in a few start-ups. In the first one, we use NLP and Computer Vision models to categorise influencers on Instagram, improving connections between brands and users. The second involves a mobile agent that moves through supermarket aisles, analysing product prices and stock-out. My job here was to develop a model capable of detecting different products to find when there is a stock-out problem or misplaced prices.
During my time as a PostDoc in Pisa, I also helped in the development of Avalanche, an End-to-End Continual Learning Library based on PyTorch.
Recent publications
- Hurtado, J., Raymond-Saez, A., Araujo, V., Lomonaco, V. and Bacciu, D. (2023). Memory Population in Continual Learning via Outlier Elimination. Workshop on Visual Continual Learning at ICCV.
- Soutif, A., Carta, A., Cossu, A., Hurtado, J., van de Weijer, J., Hemati, H., Lomonaco, V. (2023). A Comprehensive Empirical Evaluation on Online Continual Learning. Workshop on Visual Continual Learning at ICCV.
- del Rio, F., Hurtado, J., Buc Calderon, C., Soto, A. & Lomonaco, V. (2023). Studying Generalization on Memory-Based Methods in Continual Learning. The Second Workshop on Spurious Correlations, Invariance and Stability at ICML.
- Hurtado, J., Salvati, D., Semola, R., Bosio, M., & Lomonaco, V. (2023). Continual Learning for Predictive Maintenance: Overview and Challenges. Intelligent Systems with Applications.
- Villa, A., Alcázar, J. L., Alfarra, M., Alhamoud, K., Hurtado, J., Heilbron, F. C., Soto, A. & Ghanem, B. (2023). PIVOT: Prompting for Video Continual Learning. CVPR.
- Hemati, H., Cossu, A., Hurtado, J., Graffieti, G., Pellegrini, L., Carta, A., Lomonaco, V. and Borth, D., (2023) Class-Incremental Learning with Repetition. Conference on Lifelong Learning Agents.
- Araujo, V., Balabin, H., Hurtado, J., Soto, A., and Moens, MF. (2022) How Relevant is Selective Memory Population in Lifelong Language Learning? AACL-IJCNLP
- Araujo, V., Hurtado, J., Soto, A., and Moens, MF. (2022) Entropy-based Stability-Plasticity for Lifelong Learning. Workshop on Continual Learning in Computer Vision - CVPR.
- Hurtado, J., Raymond-Saez, A. and Soto, A., (2021). Optimizing Reusable Knowledge for Continual Learning via Meta-learning. NeurIPS.