Ministrante: Dr. Carlos Soares, Universidade do Porto, Portugal Resumo Metalearning consists of applying machine learning approaches to obtain models that relate the characteristics of problems with the performance of methods. Despite the potential, the metalearning field is still at an early stage of its development, with many challenges, including problem characterization, metadata collection and application Leia mais sobreRecent advances in metalearning: from metafeatures to streams[…]

Ministrante: Dr. Joaquin Vanschoren, Eindhoven University of Technology, Netherlands Resumo Building machine learning systems remains something of a (black) art, requiring a lot of prior experience to select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To democratize machine learning, and make it easily accessible to those who need Leia mais sobreDemocratizing and automating machine learning[…]

Ministrante: Dr. Ricardo Prudêncio, Universidade Federal de Pernambuco Resumo Transfer Learning is a paradigm in machine learning which aims to improve performance in a target learning domain by taking advantage of rich information available in a source domain. The literature of the area is huge and the techniques may vary a lot depending on the Leia mais sobreOverview of transfer learning[…]

Ministrante: Dr. André C. P. L. F. de Carvalho, Universidade de São Paulo Resumo After a brief introduction to the main aspects of Data Science and Machine Learning, this course will introduce how end-to-end Machine Learning solutions can be automated. For such, the historical evolution, the main approaches, with a focus on basic aspects of Leia mais sobreAutomating data science and machine learning[…]

Ministrante: Dr. Mário Gazziro, Universidade Federal do ABC Resumo Curso prático de elaboração de algoritmos acelerados para GPUs com arquitetura Pascal – será utilizada Titan XP com 3500 núcleos, porém a maioria das técnicas abordadas se aplicam a todas as classes de GPU da fabricante NVIDIA. Após introdução sobre análise do paralelismo de algoritmos, serão Leia mais sobreSuper aceleração de algoritmos usando GPUs de última geração[…]