关注
Jorge García-Carrasco
标题
引用次数
引用次数
年份
Feature engineering of EEG applied to mental disorders: a systematic mapping study
S García-Ponsoda, J García-Carrasco, MA Teruel, A Maté, J Trujillo
Applied Intelligence 53 (20), 23203-23243, 2023
142023
A methodology based on rebalancing techniques to measure and improve fairness in artificial intelligence algorithms
A Lavalle, A Maté, J Trujillo, J García Carrasco
CEUR, 2022
52022
Law modeling for fairness requirements elicitation in artificial intelligence systems
A Lavalle, A Maté, J Trujillo, J García-Carrasco
International Conference on Conceptual Modeling, 423-432, 2022
42022
Detecting and understanding vulnerabilities in language models via mechanistic interpretability
J García-Carrasco, A Maté, J Trujillo
arXiv preprint arXiv:2407.19842, 2024
32024
How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability
J García-Carrasco, A Maté, JC Trujillo
International Conference on Artificial Intelligence and Statistics, 3322-3330, 2024
32024
A data-driven methodology for guiding the selection of preprocessing techniques in a machine learning pipeline
J García-Carrasco, A Maté, J Trujillo
International Conference on Advanced Information Systems Engineering, 34-42, 2023
22023
Exploration and Implementation of Quantum Phase Estimation Algorithms
J García Carrasco
2020
A Conceptual Model-Based Approach for Exploiting Large Language Model Embeddings in Automatic Data Integration
J García-Carrasco, A Reina, A Lavalle, A Maté, J Trujillo
Available at SSRN 5024901, 0
Do Different Language Models Share Task-Specific Mechanisms? A Mechanistic Interpretability Analysis
J García-Carrasco, A Maté, J Trujillo
A Mechanistic Interpretability Analysis, 0
系统目前无法执行此操作,请稍后再试。
文章 1–9