Deep learning: Technical introduction
arXiv:1709.01412v226 citations
AI Analysis
This is an incremental pedagogical resource for learners in machine learning.
The paper provides a technical introduction to three common neural network architectures—Feedforward, Convolutional, and Recurrent—by detailing their building blocks and deriving forward pass and backpropagation rules.
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.