Backpropagation, an abbreviation for "backward propagation of errors", is a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent.
About
Stats
|
created |
8 years, 2 months ago by Franck Dernoncourt |
|
viewed |
31 times |
|
editors |
0 |
Top Answerers
more »
Recent Hot Answers
Is it possible to train a neural network without backpropagation?How is softmax_cross_entropy_with_logits different from softmax_cross_entropy_with_logits_v2?
Why are non zero-centered activation functions a problem in backpropagation?
Backpropagation with Softmax / Cross Entropy
Why is tanh almost always better than sigmoid as an activation function?
more »