Difference between revisions of "Discussion of: An Automatic Framework to Build Neural Network-based Surrogate for High-Performance Computing Applications"
Jump to navigation
Jump to search
| Line 6: | Line 6: | ||
** How is Bayesian used? (what are priors?) | ** How is Bayesian used? (what are priors?) | ||
* Feature to introduce perturbation into input features in cases where insufficient variation of data are available.(section 3.1, Step 3) | * Feature to introduce perturbation into input features in cases where insufficient variation of data are available.(section 3.1, Step 3) | ||
| − | + | * μ = 10% for hit rate test. | |
== Cissie == | == Cissie == | ||
* Slides: [https://docs.google.com/presentation/d/1Z5SXj7-yfROGzdTcfkIgT6Tg1s1a5sANaa1rxGvTHTA Auto-HPCNet vs PHASM] | * Slides: [https://docs.google.com/presentation/d/1Z5SXj7-yfROGzdTcfkIgT6Tg1s1a5sANaa1rxGvTHTA Auto-HPCNet vs PHASM] | ||
* Related Github folder by the 1st author: https://github.com/wdong5/AutoHPC-autoencoder | * Related Github folder by the 1st author: https://github.com/wdong5/AutoHPC-autoencoder | ||
Latest revision as of 17:14, 9 August 2023
David Notes
- Use of "Customized Autoencoder" to sparsify inputs is interesting.
- Are `const` parameters the primary values being filtered?
- User inputs place boundaries on accuracy and speed when optimizing topology and input features.
- How is Bayesian used? (what are priors?)
- Feature to introduce perturbation into input features in cases where insufficient variation of data are available.(section 3.1, Step 3)
- μ = 10% for hit rate test.
Cissie
- Slides: Auto-HPCNet vs PHASM
- Related Github folder by the 1st author: https://github.com/wdong5/AutoHPC-autoencoder