AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Problem With Multi-Domain Protein Faults
The training data is very small, no matter what, it's like millions. But the complexity of the protein matters here. The self-plane mechanism is a nice because it's all in simulation. So you can learn from just huge amounts, like you don't need data. There has to be, I don't know, it feels like you want to somehow 10x the data or 100x the data somehow.