AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Learning the Causality, Casuality Structure
The first question is, just how to represent the causality. And it's even harder when what the learner sees is not a causal variables, but just like low level pistles. But i think the possible free lunch here is that you can learn abstract structuren on x. and so if you learn these abstract world models, throwing away all the niddy graty, that doesn't really matter, you can potentially have very powerful, you know, predictive and coding, if you will.