Difference between revisions of "Backpropagation"
| Line 11: | Line 11: | ||
* [[Objective vs. Cost vs. Loss vs. Error Function]] | * [[Objective vs. Cost vs. Loss vs. Error Function]] | ||
* [http://en.wikipedia.org/wiki/Backpropagation Wikipedia] | * [http://en.wikipedia.org/wiki/Backpropagation Wikipedia] | ||
| + | * [http://neuralnetworksanddeeplearning.com/chap2.html How the backpropagation algorithm works] | ||
| + | * [http://hmkcode.github.io/ai/backpropagation-step-by-step/ Backpropagation Step by Step] | ||
| + | * [[Other Challenges]] | ||
| + | |||
[http://developers.google.com/machine-learning/glossary/ The primary algorithm for performing gradient descent on neural networks. First, the output values of each node are calculated (and cached) in a forward pass. Then, the partial derivative of the error with respect to each parameter is calculated in a backward pass through the graph. Machine Learning Glossary | Google] | [http://developers.google.com/machine-learning/glossary/ The primary algorithm for performing gradient descent on neural networks. First, the output values of each node are calculated (and cached) in a forward pass. Then, the partial derivative of the error with respect to each parameter is calculated in a backward pass through the graph. Machine Learning Glossary | Google] | ||
| + | |||
| + | |||
| + | http://hmkcode.github.io/images/ai/backpropagation.png | ||
| + | |||
<youtube>q555kfIFUCM</youtube> | <youtube>q555kfIFUCM</youtube> | ||
