A Self-Learning Cognitive Architecture for Scene Understanding Using Causality
El Departamento de Ingeniería Civil Eléctrica (DIE) de la Universidad de Chile, en colaboración con
la Iniciativa de Datos e Inteligencia Artificial (IDIA); el iHealth del Millennium Institute for
Intelligent Healthcare Engineering y el IEEE Computational Intelligence Society, invita a la
comunidad académica y pública a la charla magistral del distinguido profesor Jose C. Principe,
distinguished professor of Electrical and Computer Engineering, University of Florida, e IEEE
Fellow.
Bajo el título "A Self-Learning Cognitive Architecture for Scene Understanding Using Causality"
el expositor presentará avances pioneros en arquitecturas cognitivas autoaprendientes que imitan
el sistema visual animal. Esta propuesta permite reconocer objetos en videos sin necesidad de
etiquetas supervisadas, reduciendo drásticamente el ancho de banda computacional requerido.
Jose C. Principe es Distinguished Professor de Ingeniería Eléctrica, Computacional y Biomédica
en la Universidad de Florida, fundador y director del Computational NeuroEngineering
Laboratory (CNEL). Autor de más de 1.000 publicaciones, con un H-index de 104, ha dirigido 110
tesis doctorales y recibido el prestigioso IEEE Neural Network Pioneer Award en 2012. Es autor de
libros clave en el campo, como Information Theoretic Learning y Kernel Adaptive Filtering.
La actividad -en inglés- se realizará el martes 20 de enero de 2026, entre las 11:00 y 13:00 horas,
en el Auditorio Enrique D'Etigny de la Facultad de Ciencias Físicas y Matemáticas (FCFM) de la
Universidad de Chile (Beauchef 851, Santiago).
Entrada liberada con inscripción previa a través del código QR disponible en la convocatoria o
pueden ingresar AQUÍ y completar el formulario de inscripción -son cupos limitados-.
Una oportunidad imperdible para explorar las fronteras de la inteligencia artificial biológicamente
inspirada.
¡Inscríbete y no te la pierdas!
Abstract. This talk describes our efforts to abstract from the animal visual system the computational
principles to recognize objects in video without using labels and decreasing the computational
bandwidth required. We develop a hierarchical, distributed architecture of dynamical systems that
self-organizes and mimics the foveal vision in humans using an empirical Bayes criterion. The
system learns from reinforcement with the world, and uses causality to identify objects of interest
in the environment. When trained in video games its learning speed is much faster when compared
with the traditional Deep Reinforcement Learning algorithms.
Jose C. Principe (M’83-SM’90-F’00) is a Distinguished Professor of Electrical and Computer
Engineering and Biomedical Engineering at the University of Florida, where he teaches advanced
signal processing, machine learning, and artificial neural networks (ANNs) modeling. He is the Eckis
Endowed Professor and the Founder and Director of the University of Florida Computational
NeuroEngineering Laboratory (CNEL) www.cnel.ufl.edu. His primary area of interest is processing
of time-varying signals with adaptive neural models. The CNEL Lab has been studying signal and
pattern recognition principles based on information-theoretic criteria (entropy and mutual
information).
Dr. Principe is an IEEE Fellow and received the prestigious IEEE Neural Network Pioneer Award in
2012. He was the past Chair of the Technical Committee on Neural Networks of the IEEE Signal
Processing Society, Past-President of the International Neural Network Society, and Past-Editor in
Chief of the IEEE Transactions on Biomedical Engineering. Dr. Principe has more than 1000
publications, and an H-index of 104 (Google Scholar). He directed 110 Ph.D. dissertations and 66
Master theses. He wrote in 2000 an interactive electronic book entitled “Neural and Adaptive
Systems” published by John Wiley and Sons and more recently co-authored several books on
“Brain Machine Interface Engineering”, Morgan and Claypool, “Information Theoretic Learning”,
Springer, and “Kernel Adaptive Filtering”, Wiley.
Actividad con inscripción previa, a través del código QR disponible en la convocatoria o pueden
ingresar AQUÍ.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Beauchef 851
- Santiago
- Santiago, Region Metropolitana
- Chile
- Room Number: Auditorio Enrique D'Etigny