Interview With Jeremy Howard On Our Extremely Primitive Approach To ML
Jeremy Howard is a co-founder of fast.ai, the non-profit research group behind the popular massive open online course "Practical Deep Learning for Coders", and the open source deep learning library "fastai".
🎥 Watch The Full Episode At • Jeremy Howard of fast.ai— The Simple but P...
📝 Show Notes: http://wandb.me/gd-jeremy
The transcript of this short of the full interview with Jeremy Howard:
Jeremy Howard:
It’s a simple but profound insight. Which is that it’s very difficult for a model to generate something creative, and aesthetic, and correct from nothing.
The profound insight is to say, “Well, given that that’s hard, why don’t we not ask a model to do that directly? Why don’t we train a model to do something a little bit better than nothing? And then make a model that — if we run it multiple times — takes a thing that’s a little bit better than nothing, and makes that a little bit better still."
The interesting thing is that — having started to get deep into the area — I’ve realized we’re not close at all to doing that in an optimal way.
The fantastic results you’re seeing at the moment are based on what, in a year’s time, will be considered extremely primitive approaches.
Text: See the full interview at http://wandb.me/gd-jeremy