# Elementos da teoria de aprendizagem de m'aquina supervisionada

arXiv: https://arxiv.org/abs/1910.06820 · HTML: https://mlsanity.com/paper/1910.06820/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2019.

## Built on by (most cited first, 1 of 1)

- [On the Vapnik-Chervonenkis dimension of products of intervals in ℝd](https://mlsanity.com/paper/2104.07136/) (2021)

## Abstract (arXiv)

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 'e um conjunto de notas de aula para um curso introdut'orio (curso de graduacc~ao avanccado ou o 1o curso de p'os) sobre fundamentos da aprendizagem de m'aquina supervisionada (em Portugues). Os t'opicos incluem: a geometria do cubo de Hamming, concentracc~ao de medida, fragmentacc~ao e dimens~ao de Vapnik-Chervonenkis, classes de Glivenko-Cantelli, aprendizabilidade PAC, consistencia universal e o classificador k-NN em espaccos m'etricos, reducc~ao de dimensionalidade, aproximacc~ao universal, compress~ao amostral. H'a apendices sobre espaccos m'etricos e normados, teoria de medida, etc., tornando as notas autosuficientes.