Advanced search
Start date
Betweenand

Structure learning of non-stationary dynamic Bayesian networks

Grant number: 12/24272-7
Support type:Scholarships in Brazil - Doctorate (Direct)
Effective date (Start): May 01, 2013
Effective date (End): March 31, 2017
Field of knowledge:Engineering - Electrical Engineering
Principal Investigator:Carlos Dias Maciel
Grantee:Fernando Pasquini Santos
Home Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Associated scholarship(s):16/02621-0 - Dynamic Bayesian Networks for multimodal brain imaging data, BE.EP.DD

Abstract

As the use of Bayesian approaches grow in signal processing and electrophysiology researches, there is a need for study and development of optimization and machine learning techniques for the elaboration of probabilistic models known as dynamic Bayesian networks. Some application domains reveal limitations of these models, and this requires either adaptations in the original concepts such as techniques that keep a low computational cost of the learning algorithms. This is the case of systems with non-stationary and continuous signals, which will be considered in detail in this present work. We observe that the evolutive paradigm, in the area of machine learning, is a promising way for this task, due to its wide use in recent work and the quality of results that it provides (either in precision and speed). A specific application where the structure learning of a non-stationary dynamic Bayesian networks (nsDBN) comes useful is the research of the neural pathways in motor control limbs in locusts, which enables us to discover the behavior of the neuron network and apply this, later, in bioinspired robotic systems. (AU)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
SANTOS, FERNANDO P.; MACIEL, CARLOS D.; NEWLAND, PHILIP L. Pre-processing and transfer entropy measures in motor neurons controlling limb movements. Journal of Computational Neuroscience, v. 43, n. 2, p. 159-171, OCT 2017. Web of Science Citations: 1.
Academic Publications
(References retrieved automatically from State of São Paulo Research Institutions)
SANTOS, Fernando Pasquini. Neural systems identification with dynamic bayesian networks and transfer entropy. 2017. Doctoral Thesis - Universidade de São Paulo (USP). Escola de Engenharia de São Carlos São Carlos.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.