Towards Explainable AI

En Salón de Actos de la EPS IV el día 30/01/2023 a las 11:00:00

Material incluido en la colección: Federated Learning

Si no puedes visualizar correctamente este material, prueba alguna de estas opciones:
Player por defecto Usar MPEG-DASH Usar HLS Usar FLASH

Nombre Towards Explainable AI
Autor Universidad de Alicante
Título Towards Explainable AI
Resumen AI systems have become the de facto tools to solve complex problems in computer vision. Yet, it has been shown that these systems might not actually be safe to be deployed in the real world, as they too often tend to rely on dataset biases and other statistical shortcuts to achieve high performance. A growing body of research thus focuses on the development of explainability methods to better interpret these systems, to make them more trustworthy. In this talk, I will first give a general overview of the methods commonly used in eXplainable AI, before discussing the challenges that still need to be overcome by the community.
Duración 00:52:29.00
Keywords artificial intelligence inteligencia artificial ellis
Material incluido en las siguientes colecciones  
Usuario malozano[perdoname]ua.es
Tipo DIRECTO
Visitas 170
Tamaño 109.88MB