AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Deep Learning
If you don't introduce the abstract cind of structure that exists in the world, then representing p of x is very difficult. The whole point of abstraction is that it gives you very powerful abilities to jornalize to new settings,. How do we extend what we do so that it generalizes well in new settings? And thinking causily about these abstract causal dependencies as the things that are preserved across changes in distribution. If i go to the moon, it's the same laws of physics, but the distribution is very different. It's because the learner a is us.