X ValgrAI Research Morning – Innovations in Artificial Intelligence

X ValgrAI Research Morning – Innovations in Artificial Intelligence

Today, July 5th, the X ValgrAI Research Morning took place, a virtual event that brought together professionals, academics, and enthusiasts from the world of artificial intelligence. From ValgrAI, we have once again provided a space for discussion and exchange of knowledge on the latest innovations in Artificial Intelligence.

Highlighted presentations from the X ValgrAI Research Morning

Algorithm Selector for JSP through Feature Analysis

Presenter: Christian Pérez

Christian Pérez presented a framework designed to identify the key traits of the Job Shop Scheduling Problem (JSP) that characterize its complexity and guide the selection of suitable algorithms. Leveraging machine learning techniques, particularly XGBoost, the framework recommends optimal solvers such as GUROBI, CPLEX, and GECODE for efficient JSP scheduling. GUROBI excels with small instances, while GECODE demonstrates robust scalability for complex scenarios. The proposed algorithm selector achieves an accuracy of 83.44% in recommending the best algorithm for solving new JSP instances, highlighting its effectiveness in algorithm selection.

Sexism Detection in Memes

Presenter: Alba Maeso Olmos

Alba Maeso Olmos presented her study on the detection of sexist content in memes, a serious issue in today’s society due to their widespread dissemination on social media. This study focused on building a dataset of Spanish memes to perform two tasks: identifying sexism in memes and categorizing different types of sexism, such as ideological inequality, stereotypes and dominance, objectification, misogyny, and sexual violence.