evaluation question: how do you handle Deep Learning?

[thinks_ella]

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

I am particularly interested in evaluation and useful tools. I would like to compare approaches that people have actually used rather than just theoretical suggestions.

What has worked best for you, and what would you avoid?



Photo by

Please, Log in or Register to view URLs content!

on

Please, Log in or Register to view URLs content!

 

[theo_19o1]

On evaluation question: how do you handle Deep Learning?, the part about evaluation and deep stands out to me. I would test one small workflow first, keep the variables consistent, and compare the result before changing several things at once. That way you can improve the workflow without losing track of what caused the improvement.