Summary
Although artificial intelligence (AI) has improved remarkably over the last years, its inability to deal with fundamental uncertainty severely limits its application. This proposal re-imagines AI with a proper treatment of the uncertainty stemming from our forcibly partial knowledge of the world.
As currently practised, AI cannot confidently make predictions robust enough to stand the test of data generated by processes different (even by tiny details, as shown by ‘adversarial’ results able to fool deep neural networks) from those studied at training time. While recognising this issue under different names (e.g. ‘overfitting’), traditional ML seems unable to address it in non-incremental ways. As a result, AI systems suffer from brittle behaviour, and find difficult to operate in new situations, e.g. adapting to driving in heavy rain or to other road users’ different styles of driving, e.g. deriving from cultural traits.
Epistemic AI’s overall objective is to create a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties.
As currently practised, AI cannot confidently make predictions robust enough to stand the test of data generated by processes different (even by tiny details, as shown by ‘adversarial’ results able to fool deep neural networks) from those studied at training time. While recognising this issue under different names (e.g. ‘overfitting’), traditional ML seems unable to address it in non-incremental ways. As a result, AI systems suffer from brittle behaviour, and find difficult to operate in new situations, e.g. adapting to driving in heavy rain or to other road users’ different styles of driving, e.g. deriving from cultural traits.
Epistemic AI’s overall objective is to create a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/964505 |
| Start date: | 01-03-2021 |
| End date: | 28-02-2026 |
| Total budget - Public funding: | 3 016 618,75 Euro - 3 016 618,00 Euro |
Cordis data
Original description
Although artificial intelligence (AI) has improved remarkably over the last years, its inability to deal with fundamental uncertainty severely limits its application. This proposal re-imagines AI with a proper treatment of the uncertainty stemming from our forcibly partial knowledge of the world.As currently practised, AI cannot confidently make predictions robust enough to stand the test of data generated by processes different (even by tiny details, as shown by ‘adversarial’ results able to fool deep neural networks) from those studied at training time. While recognising this issue under different names (e.g. ‘overfitting’), traditional ML seems unable to address it in non-incremental ways. As a result, AI systems suffer from brittle behaviour, and find difficult to operate in new situations, e.g. adapting to driving in heavy rain or to other road users’ different styles of driving, e.g. deriving from cultural traits.
Epistemic AI’s overall objective is to create a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties.
Status
SIGNEDCall topic
FETOPEN-01-2018-2019-2020Update Date
27-04-2024
Images
No images available.
Geographical location(s)
