itschekkers

this is really just self-congratulation by them about how they have strong deal flow.

they also use this as a disingenuous/insincere way of rejecting founders (we don't want to invest, but you're probably one of the other unicorns we didn't invest in! check out out antiportfolio!)

i'm interested in the project you mentioned-- drop me an email adam at springhealth.com if you'd like to chat

There's always a PG article -- http://www.paulgraham.com/submarine.html [April 2005]

agreed

you should look into chargehound[chargehound.com], i think they would work for you.

i think its because they are correcting for the commuter tax deduction. ask your HR folks about https://www1.nyc.gov/site/dca/about/commuter-benefits-law.pa...

thanks! <3

we've had a wonderful positive response to this article, and people are overwhelmingly excited and motivated to try and exercise more because of it (even at relatively lower intensities or volumes -- every little helps). even if we are extremely cynical and say theres zero benefit of exercise for mental health, then people will still be getting known improvements regarding diabetes, stroke, cardiovascular disease. Nobody is advocating for exercise at the expense of alternative treatments like meds or therapy, this really is just a (potentially large) extra benefit.

1- surely we're allowed to waste our own time if we like!

2- nope, and actually my entire research agenda has been around helping people find a treatment that is most likely to work for them specifically! (we also founded a company to bring the research to market- springhealth.com)

3- that is beyond the scope of the paper, and we didnt use the word hospitalized once

4- yep, and thats a good example of one of the pitfalls of self-reported surveys. in general, i am a bit less cynical and in our experience, most people aren't filling out surveys to intentionally lie or sabotage.

hope this helps!

Original Article author here - happy to help with any questions people have.

Also sorry about the paywall - you can get the article either through sci-hub here http://sci-hub.tw/10.1016/S2215-0366(18)30227-X or you can email me and i'll send you a copy direct!

I hate to pour cold water on this, but medical researchers have been predicting mortality for years.

For example, here's a paper from the 1980's also predicting when a patient will die, also using a couple of thousands of patients' data: http://europepmc.org/abstract/med/3816253

And, Google's paper wasn't published in Nature, it was in a new open access journal owned by Nature. In academia, that is like the difference between a really fancy porsche, and a really cheap volkswagen (two very different things, both owned by the same company).

placebo rates would be something in the 15-40% remission rate range, in small RCTs. it varies more than you would think from one trial to another. antidepressant efficacy would be something like 20-45%. recovery rates are usually higher in smaller trials, and lower in bigger trials, partly because people get more high-touch service in smaller academic studies

theres a website called sci-hub (which maybe illegal) that you can use to get almost any paper in a STEM field, especially from major journals. you type www.sci-hub.cc/ and then paste the DOI of the paper. it takes you straight to the pdf!

Chekroud (2015) here - just wanted to say that I think SSC is awesome, and does a terrific job discussing complex problems in psychiatry & philosophy.

even in Greenpoint/Williamsburg/Bed-Stuy/Hoboken you're still paying 1500 a month to share with a few roommates though.

This post made me remember that I had muted "blockchain" on twitter, and my life was much better because of it. Classic example of adding "blockchain" or "token" to something for pure hype.

I am a client of PR, and I am algerian :)

I wonder if there are any forums/fan fiction websites where you could find big chunks of prose to add to the training data. Might help bring the loss down a bit if you mix some in.

+1 for this idea!

Ya, completely agree with this (having also used both extensively). dplyr can also connect to remote SQL server so data don't have to be local. Maybe pandas does this now too but in my experience SQL connections were generally more painful in python

my impression was that this was about the time taken to make each prediction, not to train the model? and yep, looking forward to the paper!

cool paper, i enjoyed following the post (and really appreciated the effort put into the bokeh viz!)

i wonder if this would have been improved by being clearer about the motivation. the authors frame it as though the ~60ms penalty for using the LSTM for prediction is a huge burden, and i can imagine situations where it is. however, it seems like if this is the case, we need some real life/"scaled out" examples of how this solution would work in practice. e.g. how long does the decision logic take to execute (maybe 5ms?); what proportion of the time will you have to run the LSTM after the BoW model anyway? note that those instances you are now worse off than just running the LSTM in the first place (total time = BoW time + decision time + LSTM time). once you have all these you can run the math and know (on average) how much time you'll actually save, and how much performance you sacrifice

hey, I'm not from YC nor am I rich, but we have recently founded a startup (www.spring.care) developing tools that help depressed patients identify the best antidepressant for them. I'd love to do something similar for Anxiety, or help you do it yourself. feel free to reach out to us through the website

really nice article -- easy to follow, sensible steps, clean code. I haven't done too much text ML and this was a nice piece to follow - thanks!