Moacir A. Ponti
Data Scientist Expert
Mercado Livre - Brazil
Associate Professor of Computer Science
Institute of Mathematical and Computer Sciences, Universidade de São Paulo - USP at São Carlos, Brazil
Main Research fields: Machine Learning/Representation Learning; Signal, Speech and Image Processing
In search for fair and explainable ways to apply machine learning to improve people's life.
Recent/highlighted papers (see Publication for more details):
YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone (ICML 2022)
Sketchformer: Transformer-based representation for sketched structure. (CVPR 2020)
Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask (SIBGRAPI Tutorials 2017: papers, slides, code)
Check out my Book on Machine Learning (Theory and Practice), details below!
I am recipient of a Google Latin America Research Award
At USP I have 13 years experience in teaching, as a principal investigator of many research projects and grants, and leadership, by chairing a Science Outreach committee, bridging the gap between academia, individuals, organizations and industry.
Previous experiences/education:
Academic visitor (2016-2017); Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK.
Assistant Professor (2009-2010); Universidade Federal de Viçosa, Rio Paranaíba, MG, Brazil.
PhD (2008) and MSc (2004) at the Universidade Federal de São Carlos (UFSCar), SP, Brazil.
PhD internship (2007) at IEETA, Universidade de Aveiro, Portugal.
CV: Lattes Platform CV (in Portuguese) -- CV in English (5 pgs.) [pdf]
External sites (papers, code and citations):
Github - GoogleCitations- SCOPUS - DBLP - Researcher-ID - ORCID - Linkedin
Address:
Instituto de Ciências Matemáticas e de Computação
Universidade de São Paulo - Campus de São Carlos
P.O. Box 668 / 13566-590 / São Carlos, SP, Brasil
Machine Learning: A Practical Approach on the Statistical Learning Theory
Rodrigo F. Mello . Moacir A. Ponti
Presents the Statistical Learning Theory in a detailed and easy to understand way, by using practical examples, algorithms and source codes. It can be used as a textbook in graduation or undergraduation courses, for self-learners, or as reference with respect to the main theoretical concepts of Machine Learning. Fundamental concepts of Linear Algebra and Optimization applied to Machine Learning are provided, as well as source codes in R, making the book as self-contained as possible.
Contribuições para as etapas de pré-processamento, extração de características e reconhecimento de padrões em imagens e vídeos (Tese de Livre Docência, em Portuguê)s
Moacir A. Ponti
Uma sistematização das pesquisas e trabalhos realizados pelo autor, delineando suas linhas de pesquisa, em particular no estudo das diversas etapas que compõe o pipeline do processamento de sinais, imagens e vídeos com vistas a melhoria dos sistemas de conhecimento de padrões nesses domínios. Primeiramente, são descritas as contribuições no Pré-processamento de imagens. Em segundo lugar, são apresentadas as contribuições na área de Extração de Espaços de Características. A seguir, são descritos os estudos sobre Reconhecimento de Padrões. Neste documento, são apresentados os fundamentos e os pressupostos com os quais as abordagens têm sido exploradas, destacando as contribuições e os desenvolvimentos realizados anos entre 2010-2017.