Strongly disagree with that one too. Probability is at the foundation of AI. Abandoning it means poorly calibrated over-confident models like we are seeing today. This is unacceptable in @AI_for_Science e.g. weather forecasting
@animaanandkumar
-
MBRL and MPC Integration Research Paper Discussion
By
–
https://t.co/mSB3tu3zIo combines MBRL and MPC @SahinLale @Azizzadenesheli
— Prof. Anima Anandkumar (@AnimaAnandkumar) 4 décembre 2022https://
x.com/SahinLale/stat
us/1598713083073101828?s=20&t=MHRSgSU5SlK4RIuOfgqT-g
… combines MBRL and MPC @SahinLale @Azizzadenesheli -
World Models and Reinforcement Learning in Control Theory
By
–
Agree with the last one, but we still work on a lot of reinforcement learning, because our world models are not present/perfect. @SahinLale is working at the intersection of learning and control. Check out his work for excellent theoretical background as well as empirical results
-
Generative AI Essential for Concept Learning Beyond Art Creation
By
–
Strongly disagree with the first one. "What I cannot create I cannot understand" – Richard Feynman. Generative AI is not just for creating fun art, it is at the core of concept learning.
-
AI for Science as True Test of AI Capabilities
By
–
I believe @AI_for_Science is a true test of #AI capabilities. While generating realistic text or images can be fun to play with, more controlled tests of #AI is easier with scientific domains where we have more concrete metrics and objectives to measure
-
AI for Science Community Growth at NeurIPS22
By
–
So pleased to see @AI_for_Science community grow at #NeurIPS22 When we founded AI for science initiative at @caltech in 2018, it was still considered niche. I want to thank organizers of @AI_for_Science workshop, especially student organizers who put in so much time and effort.
-
Reconnecting at NeurIPS 2022: Students and Research Groups
By
–
I have missed conference dinners. #NeurIPS2022 reunion. Great to see former students grow their research groups. Great to have students presenting at their first-ever conference. Great to connect everyone together.
-
Falcon: Model-Based RL for Extreme Turbulent Environments
By
–
— Prof. Anima Anandkumar (@AnimaAnandkumar) 3 décembre 2022
Tune in for our talk on Falcon, first model-based RL method in real-world extreme turbulent environments (Reynolds Num. 230000!), AI4Science workshop @ #Neurips2022, today @ 1:20pm. Falcon achieves 37% improvement over SOTA in stabilization of an airfoil using only 8 min of data!
-
Consciousness: Self-Awareness and Environmental Awareness in AI Systems
By
–
Consciousness is a combination of self and environmental awareness. I see environmental awareness in Minedojo as tractable but self-awareness is a different story. For that, you need uncertainty quantification is key: unknown unknowns is tricky.
-
MineDojo: Open-ended Agents for Minecraft Task Solving
By
–
Thank you @davidchalmers42 for featuring https://
minedojo.org in your talk. We build open-ended agents that can solve any task in Minecraft. This requires the agent to have awareness of the Minecraft world. Foundation models provide the agent with priors (e.g. reward function)