We are excited about TWIMLcon to hear from leaders in #MLOps across a wide variety of industries. You don't want to miss it: https://t.co/aohfw2rGuq https://t.co/SxFHezF0KS

Bayesian optimization finds the global optima relatively quickly, works well in noisy or irregular hyperparameter spaces, and efficiently explores large parameter domains. Learn the 101 of #BO from the SigOpt team: https://t.co/sSDwa0fsig

In her project with #BERT, @_notorious_meg uses distillation to create a smaller model that's still effective at question-answering. Here, she explains how distillation works to effectively compress a model: https://t.co/yy3OcnxSEp