English

Deep learning: Technical introduction

Machine Learning 2017-09-12 v2 Machine Learning

Abstract

This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building blocks are detailed. The forward pass and the update rules for the backpropagation algorithm are then derived in full.

Keywords

Cite

@article{arxiv.1709.01412,
  title  = {Deep learning: Technical introduction},
  author = {Thomas Epelbaum},
  journal= {arXiv preprint arXiv:1709.01412},
  year   = {2017}
}

Comments

The content of this note can be found on GitHub: https://github.com/tomepel/Technical_Book_DL . If you detect any typo, error, or feel that I forgot to cite an important source, don't hesitate to email: thomas.epelbaum@mediamobile.com. v2: minor typos corrected

R2 v1 2026-06-22T21:33:37.505Z