AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is There Much Work Around Interpretability in Machine Learning for Biology?
There are some problems that the general ML space is trying to solve right now. interpretability is kind of this big debate. There's also attempts to figure out how do we do low resource machine learning, dealing with cases where there isn't a lot of data. How do you get things like semi-supervised learning to work? And you would also just mention earlier that now biology is in that place where, well, we have enough data in order to make ML feasible.