hustwj

Notes on Backpropagation

Notations

Let's begin with a notation which lets us refer to weights in the network in an unambiguous way. We'll use $w_{jk}^{l}$ to denote the weight for the connection from the $k^{th}$ neuron in the $(l−1)^{th}$ layer to the $j^{th}$ neuron in the $l^{th}$ layer. So, for example, the diagram the below shows the weight on a connection from the $4^{th}$ neuron in the $2^{nd}$ layer to the $2^{nd}$ neuron in the $3^{rd}$ layer of a network: