Collaborative AI for assisting virtual laboratories
2. prosince 2022
Řečníci
Samuel Kaski
Speaker · 0 followers
O prezentaci
I will discuss two ideas: (1) virtual laboratories for science and R D, aiming to introduce an interface between algorithms and domain research that enables AI-driven scale advantages, and (2) AI-based ‘sidekick’ assistants. The purpose of the assistants is to help other agents reach their goals, even when they are not yet able to specify the goal explicitly or it is evolving. Such assistants can help with prior knowledge elicitation, at the simplest, and zero-shot assistance as the worst case. Ultimately they should be helpful for human domain experts in running experiments and solving research problems in virtual laboratories. I invite researchers to join the virtual laboratory movement: domain scientists by hosting a virtual laboratory in their field, methods researchers by contributing new methods to virtual laboratories, and human-in-the-loop ML researchers by developing the assistants.I will discuss two ideas: (1) virtual laboratories for science and R D, aiming to introduce an interface between algorithms and domain research that enables AI-driven scale advantages, and (2) AI-based ‘sidekick’ assistants. The purpose of the assistants is to help other agents reach their goals, even when they are not yet able to specify the goal explicitly or it is evolving. Such assistants can help with prior knowledge elicitation, at the simplest, and zero-shot assistance as the worst case.…
Organizátor
NeurIPS 2022
Account · 961 followers
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters
Watch later
Piera Riccio, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
Watch later
Yaqian Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model
Watch later
Yifu Yuan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Return Augmentation gives Supervised RL Temporal Compositionality
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Deep Dive into Dataset Imbalance and Bias in Face Identification
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%