Timeline for Back propagation in Convolutional neural networks
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 29, 2015 at 14:40 | comment | added | Hugh Perkins | Hmmm, fair enough :-) | |
| Apr 29, 2015 at 14:11 | comment | added | Neil G | That's usually what people mean by "backpropagation": en.wikipedia.org/wiki/Backpropagation | |
| Apr 29, 2015 at 14:02 | comment | added | Hugh Perkins | Boltzmann machine's propagate 1s and 0s randomly, according to the probabilities of their weights, in both directions, forwards and backwards. If you define backward propagation to mean propagating loss gradients, then, by your definition, boltzmann machines dont do that. | |
| Apr 29, 2015 at 13:56 | comment | added | Neil G | Not a bad answer, but Boltzmann machines don't do any "backpropagation" at all; they use contrastive divergence. Autoencoders explicitly use the source image as the target: the goal is for forward propagation (alone) to reproduce the original image; backpropagation propagates the error gradients to correct prediction error. | |
| Apr 29, 2015 at 13:44 | history | answered | Hugh Perkins | CC BY-SA 3.0 |