Francois Chollet

you are actually going to ask another deep learning model for suggestions.

Like, here's the best likely next step.

Here's where in the graph you should be going.

And you can also use yet another deep learning model for feedback.

But, well, here's what I have so far.

Is it looking good?

Should I just backtrack and try something new?

So...

think discrete program search is going to be the key but you want to make it dramatically better orders of magnitude more efficient by leveraging deep learning and by the way another thing that you can use deep learning for is of course things like common sense knowledge and knowledge in general and i think you're going to end up with this sort of system where you have this on the fly

synthesis engine that can adapt to new situations.

But the way it adapts is that it's going to fetch from a bank of patterns modules that could be themselves curves, that could be differentiable modules, and some others that could be algorithmic in nature.

It's going to assemble them via this process that's intuition-guided.

And it's going to give you, for every new situation you might be faced with, it's going to give you a generalizable model that was synthesized using very, very little data.

Something like this would sort of arc.

That's an empirical question, so I think we'll see.

Your intuition, I assume, is not that.

I'm curious why.

My intuition is, in fact, this whole system to architecture is the hard part, is the very hard and unobvious part.

Scaling up the interpretive memory is the easy part.

All you need is, like, it's literally just a big curve.