Timeline for MNIST: single layer NN with 784 neurons; is 90% error rate normal?
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 18, 2023 at 1:51 | history | edited | Sycorax♦ | CC BY-SA 4.0 |
edited title
|
| Oct 18, 2023 at 1:28 | history | edited | Arya McCarthy | CC BY-SA 4.0 |
added 28 characters in body; edited title
|
| Oct 17, 2023 at 19:26 | comment | added | Sycorax♦ | MNIST has 10 classes, so 90% error rate is no better than a random guess. Check for bugs. This problem is pretty easy, so any error rate higher than 10% suggests that whatever method you're using is deficient, has a bug, or both. | |
| Oct 17, 2023 at 19:10 | answer | added | Dave | timeline score: 2 | |
| Mar 15, 2020 at 19:27 | vote | accept | Our | ||
| Mar 14, 2020 at 12:38 | answer | added | Tim | timeline score: 3 | |
| Mar 14, 2020 at 12:19 | comment | added | Jon Nordby | You should set up the same model with an established framework and see what the performance is. 10% correct is very near to random guess rate. | |
| Mar 14, 2020 at 11:30 | comment | added | Our | @Dave current computational contraints. | |
| Mar 14, 2020 at 11:29 | comment | added | Dave | Why aren’t you training on all 60000 training samples? | |
| Mar 14, 2020 at 11:19 | history | asked | Our | CC BY-SA 4.0 |