These are public posts tagged with #AppliedML. You can interact with them if you have an account anywhere in the fediverse.
I've been tagging my tweets #appliedml rather than #amldgenai23 but same gist
"Aggressive empiricism in our culture is our enduring advantage" @mosaicml
-- Jonathan Franklin #appliedml
However you slice the data, you will always find that accuracy changes, says Kyunghyun Cho, presenting a compelling yet starkly critical view on the idea of generalised prediction models in hospital triage: an area where we can demonstrably save lives and costs to society https://www.nature.com/articles/s41586-023-06160-y #AppliedML #NYUtron
Great kickoff with Prof. Urbanke. Thanks #EPFL for having us here, and keeping the #AppliedML events open and affordable!
Glad to be following #AppliedML again today: I will cover the discussion about Generative AI in a blog post later. Check my notes from previous conferences at https://blog.datalets.ch/tag/appliedml/
Anyway, I keep meaning to write up a blog post on “falsehoods I have believed about measuring model performance” touching on #AppliedML issues related to #modelEvaluation, #metrics, #monitoring, #observability, and #experiments (#RCTs). The cool kids would call this #AIAlignment in their VC pitch decks, but even us #NormCore ML engineers have to wrestle with how to measure and optimize the real-world impact of our models.
You have a problem: you currently pick thresholds for model-based actions using some arbitrary heuristic.
Your solution: pick the threshold that maximizes expected utility (e.g. revenue, profit, ROI, …) instead. That’s the definition of the rational decision, right?
Hmm, for some reason you now seem to have several more problems.
#DecisionTheory #Optimization #rationality #AppliedML
Uncertainty about the inner workings of #machinelearning models holds back the application of ML-enabled systems in real estate markets. How do ML models arrive at their estimates?
How can practitioners guarantee that ML systems do not run afoul of the law?
Wayne Wan and I show how ML systems can be externally tested with dedicated system tests (as commonly done in software development).
#newpaperalert #appliedML #realestate #proptech #explainableML
https://onlinelibrary.wiley.com/doi/abs/10.1111/1540-6229.12416