Charla «Evaluating ML: When We will Stop Fooling Ourselves?»

📅 Martes 21 de abril | 11:00 hrs

ML Evaluation is usually based on an average measure of success such as accuracy. This kind of evaluation has several drawbacks: (1) the model works well for easy instances but badly for difficult ones, but the actual real distribution is usually not known; (2) this assumes that all errors have the same impact, which is almost never true; and (3) optimizing success does not minimize critical errors. In this presentation we discuss these problems and give some solutions that address them.

Expone: Ricardo Baeza-Yates, académico DCC UChile e investigador senior IMFD.

Lugar
Auditorio Ramón Picarte
Facultad de Cs. Físicas y Matemáticas
Universidad de Chile

Dirección
Beauchef 851, edificio norte, 3er piso
Ver mapa

Fecha del evento
21 de Abril de 2026
11:00 – 12:30

Organizador Departamento de Ciencias de la Computación contacto@dcc.uchile.cl

— Comunicaciones DCC