AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Curse of Dimensionality in Machine Learning
So we've been listening to quite a few folks that make the argument about the interpretive nature of deep learning. And you could argue that any kind of processing in machine learning, not just feature transformations orleaving things like regularization and domain randomization, would be appropriate for an interpolative problem. That's what these people say. But why do you think that deep learning works at all in these high dimensional spaces? We sa first i might say something o bite, say, speculative or not agreed upon by everyone, but i don't seem we loveit. We love it. Please do a i don't think you can state so generally that the planning walks, right? You need