Deep learning: Technical introduction

2017/09/05 by Thomas Epelbaum, Epelbaum, Thomas · 1 voice
#stat.ML #cs.LG

paper · pdf · doi:10.48550/arxiv.1709.01412

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.

Discussions

• Deep learning: Technical introduction [hn, 6 points, 0 comments]

Related

• Forward Thinking: Building and Training Neural Networks One Layer at a Time
• Deep Neural Networks - A Brief History
• Lecture Notes: Neural Network Architectures
• Deep learning for pedestrians: backpropagation in CNNs
• Deep learning: an overview and main paradigms