I'm a full professor at Johns Hopkins University in the US and at EPFL in Switzerland. You know, those machines, they can build new images that we've never seen before, or say new sentences that were never heard before.
Why listen
It goes beyond the title with direct discussion of it's, know, think, including: You know, those machines, they can build new images that we've never seen before, or say new sentences that were never heard before.
Key takeaways
01You know, those machines, they can build new images that we've never seen before, or say new sentences that were never heard before
02And so what we've been doing over the years is trying to build a framework based on physics that's really tried to answer those different questions in a unified manner
03But if you have a deep architecture, there is a huge implicit bias to build those coarse-grained variables
Best for
research-minded practitioners comparing model behavior