Recent advances in metalearning: from metafeatures to streams

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[…]

Democratizing and automating machine learning

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[…]

Automating data science and machine 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[…]

Super aceleração de algoritmos usando GPUs de última geração

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[…]