filmov
tv
When to trust AI, Marta Kwiatkowska (Trinity College, University of Oxford)
Показать описание
Machine learning solutions are revolutionizing AI, but their instability against adversarial examples—small perturbations to inputs that can catastrophically affect the output—raises concerns about the readiness of this technology for widespread deployment.
Marta Kwiatkowska uses illustrative examples to give you an overview of techniques being developed to improve the robustness, safety, and trust in AI systems.
Follow O'Reilly on:
Marta Kwiatkowska uses illustrative examples to give you an overview of techniques being developed to improve the robustness, safety, and trust in AI systems.
Follow O'Reilly on:
0:04:32
0:06:57
1:25:19
0:57:39
0:52:50
0:56:03
1:11:13
0:14:58
0:33:45
1:02:07
0:28:59
0:00:15
0:08:08
0:01:00
0:37:01
0:22:31
1:02:07
0:29:17
0:19:47
0:43:42
0:19:59
0:14:54
0:03:52
0:16:06