Related Posts
Is it a good time to buy properties in nyc?
Additional Posts in Data & Analytics Consultants
Thought this was interesting. Across 160 teams of researchers, just about all failed to make good life outcome predictions on things like GPA, evictions, layoffs, and others. Data followed 4.5k families across 15 years, with 13k features (varied over time). Haven't looked at it directly yet, but will be turning the docs and data inside out... In the meantime, authors claim this as showing the limits of ML. Oh, and it's published in PNAS, so you know there's some big publication energy there.
https://www.pnas.org/content/117/15/8398
What is a data lake in basic terms?
New to Fishbowl?
unlock all discussions on Fishbowl.



Might be a dumb question, but how’d you build it if you don’t know how it works? Or is this one of those accidental inventions? lol
So beautiful! My fave data scientist once said if I didn’t have google I couldn’t write one line of code
Very interested in this! Are you using publicly available datasets? Is the model built from ‘scratch’ - i.e. modelling intermolecular forces, or is it more based on an analysis of ‘if this molecule works as a drug then there is a likelihood that this one should too’, without any of the physics?
The network learns graphs representing molecular structures. Generated molecules are validated w.r.t. feasibility after the fact, with degree of validity as one of the metrics (alongside uniqueness of proposals one to another, and novelty vs known graphs)