Miles Cranmer -...
Original video. A brief summary of the ideas: Part 1 PySR -- a symbolic regression solver, which fits the data by finding a mathematical expression via genetic algorithms. This solver could be used to fit the output of a conventional neural network. The key part is that a neural network could be dissected and fit part by part. We obviously can't do this with the raw data, but using a conventional neural network as an approximator allows us to get a number of smaller and simpler relations and fit them with the symbolic regression. Part 2 Using pre-learned models helps, it is especially visible in NLP. It probably works [citation needed] because different domains have shared areas (like, for example, all the modern languages sharing the notions of grammar, punctuation, etc.), thus extending the dataset gives models an expected boost in performance. Actually, different areas of science also have shared concepts, so it'd be good to find a way to use them. The corresponding project is...