Hybrid Convolutional Neural Networks with Reliability Guarantee
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917662055989248 |
|---|---|
| author | Doran, Hans Dermot Veljanovska, Suzana |
| author_facet | Doran, Hans Dermot Veljanovska, Suzana |
| contents | Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties. Typical redundancy techniques incur at least double or triple the computational expense of the original. We adopt a co-design approach, integrating reliable model execution with non-reliable execution, focusing that additional computational expense only where it is strictly necessary. We describe the design, implementation and some preliminary results of a hybrid CNN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_05146 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hybrid Convolutional Neural Networks with Reliability Guarantee Doran, Hans Dermot Veljanovska, Suzana Artificial Intelligence Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties. Typical redundancy techniques incur at least double or triple the computational expense of the original. We adopt a co-design approach, integrating reliable model execution with non-reliable execution, focusing that additional computational expense only where it is strictly necessary. We describe the design, implementation and some preliminary results of a hybrid CNN. |
| title | Hybrid Convolutional Neural Networks with Reliability Guarantee |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.05146 |