Challenges in Machine Learning, from Proactive to Transfer Learning

11.30 a 13.00
Sala de Conferencias, Río Hondo
Avisos Varios
Challenges in Machine Learning, from Proactive to Transfer Learning

Dr. Jaime Carbonell del Carnegie Mellon University

Machine Learning is rapidly becoming ubiquitous in computation, from deep learning for images, speech and language to large-scale data mining and decision support. But some major challenges remain including: 1) how to cope with sparse expert answers (labels) to train accurate models, 2) how to explain the learned behaviors, 3) how to combine knowledge and constraints with data, especially when the latter is scarce.  The presentation will introduce proactive learning from multiple sources, transfer/multi-task learning, and address issues in application of these methods to different areas, such as natural language processing and computational biology

Organiza: 
Departamento Académico de Computación
División Académica de Ingeniería

Informes

Mantente en Contacto
Todos los derechos reservados © ITAM, 2017. Río Hondo No.1, Col. Progreso Tizapán, Álvaro Obregón, 01080 Ciudad de México, México, Tel. +52(55) 5628 4000