New answers tagged

2 votes
Accepted

Does this article make use of the chain rule? And where?

Unless the derivation has been added in a comment, when you read code implementations of backpropagation, then the chain rule has already been used to derive the update rules. As it is basically a ...
Neil Slater's user avatar
  • 30.2k
2 votes
Accepted

In multilayer perceptron neural networks, are the names "delta", "gradient" and "error" all the same thing? or not?

The terms "error", "delta" and "gradient" in neural network back-propagation are often used as shorthand, or loose explanations for the same thing. This is not strictly ...
Neil Slater's user avatar
  • 30.2k

Top 50 recent answers are included