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.
arXiv 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
Linked by 2 identifiable commenters in 2 comments across 1 thread, from Sep 2017 to Sep 2017. Found in 1 HN submission from Sep 2017 to Sep 2017. Open submission discussions.
Here's a post from yesterday with a link to the PDF: https://news.ycombinator.com/item?id=15186249 Points to this: https://arxiv.org/abs/1709.01412
mellingView on HNParent context
arxiv link https://arxiv.org/abs/1709.01412
md8View on HNParent context