Deep Learning: Technical Introduction
by Thomas Epelbaum
Publisher: arXiv.org 2017
Number of pages: 106
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.
Download or read it online for free here: