Sign in

Tarin Ziyaee

@tarinz.bsky.social
26 followers 13 following 8 posts
PostsRepliesMedia
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
But this is where the tweet ends - and the paper begins. Great work by @joelbot3000.bsky.social, Elliot Meyerson, Tarek El-Gaaly, Ken Stanley, and yours truly. Paper: arxiv.org/abs/2501.13075
arxiv.org
Evolution and The Knightian Blindspot of Machine Learning
This paper claims that machine learning (ML) largely overlooks an important facet of general intelligence: robustness to a qualitatively unknown future in an open world. Such robustness relates to Kni...
031
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
Knightian Uncertainty - and how evolution and life dealt with it - have huge implications and insights on how robust Intelligence operates in the world, AS IS.
110
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
In other words: Anticipating the predictable and training for it, VS Acknowledging unpredictability and dealing with it - as it unfolds.
110
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
In the paper, we contrast search solutions from nature that have worked: Persist & Filter, in the face of KU, (Nature's predominant paradigm) VS Anticipate & Train, ignoring KU. (ML's predominant paradigm)
121
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
Knightian Uncertainty - the notion that the sample space cannot be exhaustively anticipated - is a fundamental property of unstructured open-ended environments. Also known as, the real world.
110
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
In closed and controlled environments, ML generalization can take us a long way. But what if we're dealing with unstructured open-ended environments AS IS?
110
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
Physical AI systems are (still!) plagued with so called "corner cases" and "long tails". But why? The impact is real. The stakes are high.
120
Tarin Ziyaee @tarinz.bsky.social · 24/01/2025
"Corner cases". "Long tails". You can play whack-a-mole with them. Or, you can confront their root causes directly. Our new paper "Evolution and The Knightian Blindspot of Machine Learning" argues we should do the latter.
2178