As an aside, does anyone have any machine learning...

# datascience

[dalexander]

As an aside, does anyone have any machine learning books their recommend? What qualities make a ML book good? I know there have been significant improvements in how good we are at building neural networks in the last several years, so I have to imagine suggestions would need to be more recent?

[thomasnield]

A good ML book is one that's focused and clear on the specific task you have in mind. This is a great book to get an overview conceptually of different ML tasks. http://a.co/hKEtUXT

[dalexander]

Thanks for the suggestion. And that makes sense, I guess that also explains why there’s a lot of “Using ML to do <very specific thing>” material floating around as well.

[dalexander]

Interesting overview of “which tool solves which problem”.

[thomasnield]

@dalexander that is a question you must constantly ask yourself if you want to be productive.

[dalexander]

I suppose. For work I don’t usually get asked that kind of question, personal projects tend to be more open ended, but I’m also more than willing to spend time frivolously to learn more about something.

[thomasnield]

@derek Definitely I'm kind of in that situation too. In that case, it's best to have your personal project be something specific and challenging as possible.