LESSWRONG
LW

stared
2030
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
Learning Deep Learning the EASY way, with Keras
stared8y00

Author of Learning Deep Learning here.

How to solve a practical problems requires much more well-rounded skills that mastering one machine learning algorithm or another (in fact, some problems don't require ML at all).

For a more general introduction to data science, see http://p.migdal.pl/2016/03/15/data-science-intro-for-math-phys-background.html. So yes: discussing things with clients, getting data, cleaning data, realising it is not enough, so asking client if they have more/different data, exploring it, seeing that some of it is rubbish, semi-manually cleaning it, creating a model, seeing it's ok, discovering that it fitted to some artefact, ... (and dozens, dozens of steps).

Reply
Meetup : First LW Meetup in Warsaw
stared11y00

This link does not work for me (it redirects to my event list). I am not sure if it is because of privacy settings or anything else? In any case: what is its full name as it appears on FB?

Reply
Meetup : First LW Meetup in Warsaw
stared11y20

I am interested, but not sure if I will be available on that date (40%?). Do you want to create a FB event? From my experience as an organizer of various stuff it works for seeing who is interested; of course it will attract more newbies and casual readers (I am in this category: up to date, my most serious interaction with LW is this post: http://stats.stackexchange.com/questions/28067/entropy-based-refutation-of-shalizis-bayesian-backward-arrow-of-time-paradox/28634#28634).

Reply
No wikitag contributions to display.
No posts to display.