LGOct 6, 2019

Elementos da teoria de aprendizagem de máquina supervisionada

arXiv:1910.06820v11 citations
Originality Synthesis-oriented
AI Analysis

It provides educational material for advanced undergraduates or first-year graduate students, but it is incremental as it compiles existing theory without new research contributions.

This paper presents lecture notes for an introductory course on the foundations of supervised machine learning, covering topics such as VC dimension, PAC learnability, and universal consistency, with appendices to make the material self-contained.

This is a set of lecture notes for an introductory course (advanced undergaduates or the 1st graduate course) on foundations of supervised machine learning (in Portuguese). The topics include: the geometry of the Hamming cube, concentration of measure, shattering and VC dimension, Glivenko-Cantelli classes, PAC learnability, universal consistency and the k-NN classifier in metric spaces, dimensionality reduction, universal approximation, sample compression. There are appendices on metric and normed spaces, measure theory, etc., making the notes self-contained. Este é um conjunto de notas de aula para um curso introdutório (curso de graduação avançado ou o 1o curso de pós) sobre fundamentos da aprendizagem de máquina supervisionada (em Português). Os tópicos incluem: a geometria do cubo de Hamming, concentração de medida, fragmentação e dimensão de Vapnik-Chervonenkis, classes de Glivenko-Cantelli, aprendizabilidade PAC, consistência universal e o classificador k-NN em espaços métricos, redução de dimensionalidade, aproximação universal, compressão amostral. Há apêndices sobre espaços métricos e normados, teoria de medida, etc., tornando as notas autosuficientes.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes