Backpropagation of Machine Learning

Last updated on:17 days ago

Backpropagation is a rather basic concept of machine learning. I want to write a concise review here.

Classes review version

Andrew NG

$a^{(i)}$ is output, $z^{(i)} or x$ is input, $\theta^{(i))$ is weight, $g()$ is activation function

Compute the delta terms for the earlier layer.

Training a neural network steps


[1] Backpropagation

[2] Andrew NG, Machine learning