Defesa de Proposta de Dissertação: Diego Parente Paiva Mesquita

Título: Machine learning for incomplete data.

Data: 13/06/2017 Horário: 10h Local: Sala de Seminários do Bloco 952 - Campus do Pici

Resumo:

Methods based on similarity measures such as distances or kernel functions are widely used in machine learning and related fields. These methods often take for granted that data is fully observed and are not equipped to handle incomplete data in an organic manner. This assumption is often flawed, as incomplete data is a fact in various domains such as medical diagnosis and sensor analytics. Therefore, one might find it useful to be able to estimate these distances/kernels in the presence of partially observed data. We propose methodologies to estimate the Gaussian Kernel, the Euclidean Distance and the Epanechnikov kernel between possibly incomplete feature vectors.

Banca:

  • Prof. Dr. João Paulo Pordeus Gomes (MDCC/UFC - Orientador)
  • Prof. Dr. João Fernando Lima de Alcântara (MDCC/UFC)
  • Prof. Dr. José Antônio Fernandes de Macêdo (MDCC/UFC)