Discover and read the best of Twitter Threads about #MachineLearing
Most recents (2)
1/4 If you read one #depression #biomarker paper this year, read this one by Nils & the gang. They looked at a large sample of depressed and healthy participants, investigating numerous features (neuro, genetics, etc) in 2.4 million #MachineLearing models.
2/4 I'm not surprised by the results: depression is not a unitary, biological disease entity. It is a label that was historically developed for clinical utility: it is a heuristic superimposed on a complex landscape of mental health problems people experience.
3/4 The label has strenghts (and I believe labels can be helpful), but of course biological investigations into labels such as depression will have limited success.
This view is summarized in 2 recent papers:
This view is summarized in 2 recent papers:
I'm so happy to publicly release the #MachineLearing course I've been developing over the past 4 years, through 5 iterations, first for @NYUDataScience and later for @TechAtBloomberg's 5,000+ software engineers in our #ML EDU initiative. techatbloomberg.com/foml/
Thanks @david_sontag for connecting me to @NYUDataScience and @roy_lowrance and @jfreirenet for hiring me.
At Bloomberg, thanks to @gideonmann, Jeanette Bashford, Shawn Edwards, Vlad Kliatchko, and Zoey Deng for supporting the project from inception to its public release.
