Timeline for Cost function spiking upon using dropout on neural network
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 13, 2018 at 3:33 | answer | added | Sycorax♦ | timeline score: 1 | |
| Feb 8, 2016 at 9:37 | comment | added | arch3r | @IndieAI : Yes, I am performing a learning rate decay. I corrected this problem for a Neural Network by multiplying the weights with a scale, but it seems to persist for autoencoders while using denoising technique | |
| Dec 28, 2015 at 17:39 | comment | added | Indie AI | Are you decreasing the learning rate as you are training? | |
| S Oct 5, 2015 at 17:57 | history | suggested | Franck Dernoncourt |
add dropout tag
|
|
| Oct 5, 2015 at 17:13 | review | Suggested edits | |||
| S Oct 5, 2015 at 17:57 | |||||
| Aug 28, 2015 at 16:40 | review | First posts | |||
| Aug 28, 2015 at 16:42 | |||||
| Aug 28, 2015 at 16:37 | history | asked | arch3r | CC BY-SA 3.0 |