Timeline for How to give assignments that require heavy computational resources?
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 9, 2018 at 6:30 | comment | added | DonFusili | @Discretelizard Sure, deep learning only gives good results on initial training on large datasets. Then the industry found a workaround for that and transfer learning is the main way of making working nets. This is completely doable with standard laptops. | |
| Apr 8, 2018 at 15:26 | comment | added | Discrete lizard | While I understand the advice given in the first paragraphs, I was already aware of this and think that has been one of the problems. This might be a good time to mention that I'm not the one responsible for designing the assignment, but a concerned grading assistant. Of course, this doesn't make your advice less valuable, merely less useful to me in particular. As for 'scaling down', that would be difficult. Deep learning only gives reasonable results on large datasets, as far as I'm aware. I do think that perhaps 'scaling out' might be possible: circumvent the actual computations, somehow. | |
| Apr 8, 2018 at 15:21 | history | answered | Buffy | CC BY-SA 3.0 |