How do you improve customisation when working with Deep Learning?

[mayasouth]

I am trying to improve my approach to Deep Learning and could use some practical advice.

I am particularly interested in customisation and cost control. I would like to compare approaches that people have actually used rather than just theoretical suggestions.

Which approach would you recommend and why?



Photo by

Please, Log in or Register to view URLs content!

on

Please, Log in or Register to view URLs content!

 

[ellatherunner]

The point about improve and customisation is interesting. In practice I would keep the first test simple, record what worked, and only add extra complexity if it solves a specific limitation. The original point — "I am trying to improve my approach to Deep Learning and could use some practical advice. I am particularly interested in customisation and cost control. I would like to compare ap…" — gives a useful starting point for that comparison.