Go to:
Esta página em português Ajuda Autenticar-se
Formação de utilizadores da Biblioteca: 2º semestre de 2017/18
Você está em: Start > Notícias > DEEC Talks: Time Based Computation with Pulse Trains

Campus Map
Edifício A (Administração) Edifício B (Aulas) - Bloco I Edifício B (Aulas) - Bloco II Edifício B (Aulas) - Bloco III Edifício B (Aulas) - Bloco IV Edifício C (Biblioteca) Edifício D (CICA) Edifício E (Química) Edifício F (Minas e Metalurgia) Edifício F (Minas e Metalurgia) Edifício G (Civil) Edifício H (Civil) Edifício I (Electrotecnia) Edifício J (Electrotecnia) Edifício K (Pavilhão FCNAUP) Edifício L (Mecânica) Edifício M (Mecânica) Edifício N (Garagem) Edifício O (Cafetaria) Edifício P (Cantina) Edifício Q (Central de Gases) Edifício R (Laboratório de Engenharia do Ambiente) Edifício S (INESC) Edifício T (Torre do INEGI) Edifício U (Nave do INEGI) Edifício X (Associação de Estudantes)

DEEC Talks: ''Time Based Computation with Pulse Trains''

19th July | 11h30 | Room I-105 DEEC FEUP

Numeric computation is at the core of man-made computation models and its mathematical foundations are very well understood. However, we humans very likely do not use the same principles. This talk describes efforts to think out of the digital computation box and searches for alternate computational methodologies with pulse trains. After a brief introduction, the integrate-and-fire converter is presented to convert analog signals into pulse trains with properties similar to Nyquist sampling (reconstruction with an error as small as desired). However, there are still many unanswered questions that may be of interest for this community. We present a methodology that converts input data streams in pulse trains, statistically trains recurrent kernel filters and then deploys the system in ultra-low power finite state machines without the need for digital computers. Performance is comparable to the best digital methodologies.

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 BellSouth 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. 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 800 publications.  He directed 93 Ph.D.dissertations and 65 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.


 Disclose your events and projects by e-mailnoticias@fe.up.pt. Find out more about our services in SICC site.


Recomendar Página Voltar ao Topo
Copyright 1996-2018 © Faculdade de Engenharia da Universidade do Porto  I Termos e Condições  I Accessibility  I Índice A-Z  I Guest Book
Page generated on: 2018-05-23 at 06:02:51