Machine learning using models inspired by nature

• Grant number: 11/17396-9
• Support Opportunities: Research Grants - Young Investigators Grants
• Start date: March 01, 2012
• End date: February 29, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Fabricio Aparecido Breve
• Grantee: Fabricio Aparecido Breve
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil
• Associated researchers: Zhao Liang
• Associated scholarship(s): 15/06780-3 - Applying Inspired Algorithms for Nature to Classification of depolymerase Enzyme Used in Biofuel Production, BP.MS

Abstract

Nature-inspired computation is the name given to the set of techniques to solve computational problems, which design used nature as source of inspiration. Computational models inspired by nature are frequently used in tasks of machine learning, a research field dedicated to the project and development of algorithms which allow computers to evolve behavior based on empirical data. Recently, some works using intelligent particles, which walk through networks delimiting territory through competition and cooperation mechanisms, were used in some machine learning tasks. The main objective of this project is to create and/or adapt models inspired by nature, including particles movement models, to solve some specific machine learning problems, including the problem of learning from imperfect data, where some data items have wrong labels; and the problem of detecting overlapped communities, where several elements may belong, at the same time, to more than one community with different pertinence degrees. It is also intended to extend such models to other computer science areas and even other disciplines. Another objective of this project is to implement these nature-inspired models to execute in GPU (Graphics Processing Unit). (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)

BREVE, FABRICIO A.; ZHAO, LIANG; QUILES, MARCOS G.. Particle competition and cooperation for semi-supervised learning with label noise. Neurocomputing, v. 160, p. 63-72, JUL 21 2015. (11/17396-9, 13/07375-0, 11/50151-0, 11/18496-7)

BREVE, FABRICIO APARECIDO; GUIMARAES PEDRONETTE, DANIEL CARLOS; IEEE. COMBINED UNSUPERVISED AND SEMI-SUPERVISED LEARNING FOR DATA CLASSIFICATION. 2016 IEEE 26TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), v. N/A, p. 6-pg., 2016-01-01. (11/17396-9, 13/08645-0)