
22 - Shard Theory with Quintin Pope
AXRP - the AI X-risk Research Podcast
The Inductive Biases of Machine Learning Systems
There are various similarities between human brains and neural networks they have like similar representations of language the learning process is biased towards like similar kinds of results does that about cover it? Well there's this thing called singular learning theory in the study of machine learning systems. It looks at how the data that the system is trained on influences the inductive biases of the system. There are even results that no purely architecture level explanation of inductive biases can fully account for them.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.