Follow

1 The statistical problem is only a proxy
2 Nature does not shuffle the examples. We shouldn't
3 Invariance across environments buys extrapolation powers
4 Invariance across environments is related to causation
5 Invariant representations enable invariance

Tag yourself - I'm #2

RT @NandoDF@twitter.com

Great insights on learning from Leon Bottou

🐦🔗: twitter.com/NandoDF/status/112

Sign in to participate in the conversation
Mastodon

Some people know that there are many possible futures. And once you accept this possibility - well, then you want to play your part getting us onto the best timeline possible. If you're one of these people - wherever you are, whatever you do, however you view your talents - this is the place for you.