AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Do You Approach Pre Training and Self Supervition for Biological Systems?
In many ways, theer like the the single cell. And again, i asor we're going deep on the single cell world, cause especially it's like what i know the best and it's what imeni a focuses on. The field literally didn't exist five years ago. Five years ago, people published papers on 200 cells. Now we're publishing on two million. So just like the scale of the data in the last five years has enabled a certain new flavor of models that just didn't exist, you couldn't do before. We're benefiting from other people doing this kind of pre training and transfer architecture for biological system scause. I'm wondering if you could describe this