Matches in SemOpenAlex for { <https://semopenalex.org/work/W3031885648> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3031885648 abstract "We explore in detail a method to solve ordinary differential equations using feedforward neural networks. We prove a specific loss function, which does not require knowledge of the exact solution, to be a suitable standard metric to evaluate neural networks' performance. Neural networks are shown to be proficient at approximating continuous solutions within their training domains. We illustrate neural networks' ability to outperform traditional standard numerical techniques. Training is thoroughly examined and three universal phases are found: (i) a prior tangent adjustment, (ii) a curvature fitting, and (iii) a fine-tuning stage. The main limitation of the method is the nontrivial task of finding the appropriate neural network architecture and the choice of neural network hyperparameters for efficient optimization. However, we observe an optimal architecture that matches the complexity of the differential equation. A user-friendly and adaptable open-source code (ODE$mathcal{N}$) is provided on GitHub." @default.
- W3031885648 created "2020-06-05" @default.
- W3031885648 creator A5005923000 @default.
- W3031885648 creator A5006912002 @default.
- W3031885648 date "2020-05-28" @default.
- W3031885648 modified "2023-09-27" @default.
- W3031885648 title "ODEN: A Framework to Solve Ordinary Differential Equations using Artificial Neural Networks." @default.
- W3031885648 cites W1506806321 @default.
- W3031885648 cites W2022709125 @default.
- W3031885648 cites W2939928718 @default.
- W3031885648 cites W2963302407 @default.
- W3031885648 cites W3018499229 @default.
- W3031885648 hasPublicationYear "2020" @default.
- W3031885648 type Work @default.
- W3031885648 sameAs 3031885648 @default.
- W3031885648 citedByCount "0" @default.
- W3031885648 crossrefType "posted-content" @default.
- W3031885648 hasAuthorship W3031885648A5005923000 @default.
- W3031885648 hasAuthorship W3031885648A5006912002 @default.
- W3031885648 hasConcept C11413529 @default.
- W3031885648 hasConcept C126255220 @default.
- W3031885648 hasConcept C134306372 @default.
- W3031885648 hasConcept C14036430 @default.
- W3031885648 hasConcept C154945302 @default.
- W3031885648 hasConcept C162324750 @default.
- W3031885648 hasConcept C176217482 @default.
- W3031885648 hasConcept C177264268 @default.
- W3031885648 hasConcept C195065555 @default.
- W3031885648 hasConcept C199360897 @default.
- W3031885648 hasConcept C21547014 @default.
- W3031885648 hasConcept C2524010 @default.
- W3031885648 hasConcept C2776760102 @default.
- W3031885648 hasConcept C28826006 @default.
- W3031885648 hasConcept C33923547 @default.
- W3031885648 hasConcept C34862557 @default.
- W3031885648 hasConcept C41008148 @default.
- W3031885648 hasConcept C47702885 @default.
- W3031885648 hasConcept C50644808 @default.
- W3031885648 hasConcept C51544822 @default.
- W3031885648 hasConcept C78045399 @default.
- W3031885648 hasConcept C78458016 @default.
- W3031885648 hasConcept C8642999 @default.
- W3031885648 hasConcept C86803240 @default.
- W3031885648 hasConceptScore W3031885648C11413529 @default.
- W3031885648 hasConceptScore W3031885648C126255220 @default.
- W3031885648 hasConceptScore W3031885648C134306372 @default.
- W3031885648 hasConceptScore W3031885648C14036430 @default.
- W3031885648 hasConceptScore W3031885648C154945302 @default.
- W3031885648 hasConceptScore W3031885648C162324750 @default.
- W3031885648 hasConceptScore W3031885648C176217482 @default.
- W3031885648 hasConceptScore W3031885648C177264268 @default.
- W3031885648 hasConceptScore W3031885648C195065555 @default.
- W3031885648 hasConceptScore W3031885648C199360897 @default.
- W3031885648 hasConceptScore W3031885648C21547014 @default.
- W3031885648 hasConceptScore W3031885648C2524010 @default.
- W3031885648 hasConceptScore W3031885648C2776760102 @default.
- W3031885648 hasConceptScore W3031885648C28826006 @default.
- W3031885648 hasConceptScore W3031885648C33923547 @default.
- W3031885648 hasConceptScore W3031885648C34862557 @default.
- W3031885648 hasConceptScore W3031885648C41008148 @default.
- W3031885648 hasConceptScore W3031885648C47702885 @default.
- W3031885648 hasConceptScore W3031885648C50644808 @default.
- W3031885648 hasConceptScore W3031885648C51544822 @default.
- W3031885648 hasConceptScore W3031885648C78045399 @default.
- W3031885648 hasConceptScore W3031885648C78458016 @default.
- W3031885648 hasConceptScore W3031885648C8642999 @default.
- W3031885648 hasConceptScore W3031885648C86803240 @default.
- W3031885648 hasLocation W30318856481 @default.
- W3031885648 hasOpenAccess W3031885648 @default.
- W3031885648 hasPrimaryLocation W30318856481 @default.
- W3031885648 hasRelatedWork W1980532470 @default.
- W3031885648 hasRelatedWork W2035199972 @default.
- W3031885648 hasRelatedWork W2054126364 @default.
- W3031885648 hasRelatedWork W2070210891 @default.
- W3031885648 hasRelatedWork W2130170304 @default.
- W3031885648 hasRelatedWork W2291317298 @default.
- W3031885648 hasRelatedWork W2325799880 @default.
- W3031885648 hasRelatedWork W2616451138 @default.
- W3031885648 hasRelatedWork W2770250658 @default.
- W3031885648 hasRelatedWork W2810013035 @default.
- W3031885648 hasRelatedWork W2887532679 @default.
- W3031885648 hasRelatedWork W2971538460 @default.
- W3031885648 hasRelatedWork W3003607224 @default.
- W3031885648 hasRelatedWork W3081725187 @default.
- W3031885648 hasRelatedWork W3167040424 @default.
- W3031885648 hasRelatedWork W3169059994 @default.
- W3031885648 hasRelatedWork W3176613710 @default.
- W3031885648 hasRelatedWork W3196094225 @default.
- W3031885648 hasRelatedWork W3202725229 @default.
- W3031885648 hasRelatedWork W2163422751 @default.
- W3031885648 isParatext "false" @default.
- W3031885648 isRetracted "false" @default.
- W3031885648 magId "3031885648" @default.
- W3031885648 workType "article" @default.