Backpropagation, or backprop, is used to efficiently calculate the gradient of the cost function, C. In simple terms, the goal of backprop is to compute the rate of change of the cost, C, with respect to the weights, (
), and the biases, (
).
In order to clarify the intuition behind backprop, let's consider following deep neural network:
Imagine that we have made a small change, , in the weight value of some weight, , in the network. ...
Get Artificial Intelligence for Big Data now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now