mathperson

did nassim taleb really boast about deadlifting 400 lbs? That isn't very much for a deadlift if you lift consistently...

at the risk of offending NLPers/Vision/Speech I just think those tasks are 'easier' in a variety of ways.

I'm actually not familiar with this exam-I'll look into it!

myer briggs is basically meaningless

lol what-I was looking at this list of people who do this-in fact a lot of them ARE machine learning researchers...including some in my department!

I'm frustrated that is patentable

It was called the tpp...

and he finds this hard to believe after a power (russia) interfered massively in an american election? an in europe...

what is lecunn paid by FAIR? my roommate and I settled on 2-3 mil. thoughts?

Fantastic!

I thought more about your question (at least what I thought it was) and it wouldn't necessarily prevent redundant encoding but it would sort of restrict how 'damaging' such an encoding could be (if that makes sense).

This whole field is very new but very exciting and very troubling.

Like- what is fairness really? Its an intersection of philosophy/ethics and very UN-intuitive mathematics..there are many open questions

I don't like this example-they could be a graduate student

I am going to assume by 'redundant encoding' you mean a model that takes some non-racial feature like- living in an urban area- and uses that to predict something that is very different across races- say whether or not your loan is approved.

"Definition 2.1 (Equalized odds). We say that a predictor Yhat satisfies equalized odds with respect to protected attribute A and outcome Y , if Yhat and A are independent conditional on Y ."

This is from page 3. Yhat is the model trained on A (protected class) T (training outcome).

Do you see how if this definition holds there can be absolutely no redundant encoding?

I think a great part is you can watch someone take a REAL potato with real dirt on it, clean it, cut it up with a massive guillotine thing, insert it into boiling oil, and hand it to you. Beautiful.