Ask HN: Is machine learning worth learning for hobbyists/pet projects?

Re:Ask HN: Is machine learning worth learning for hobbyists/... by chas on Friday May 04, 2018 @02:12PM (#16996821)

Machine learning is a bigger set of techniques than deep learning. Linear regression and random forests still work fine and can get good results in many problem domains without particularly much compute hardware. In addition non-learned feature engineering can get good results in computer vision if you constrain your input images.

Do you have particular application areas or problems you want to apply ML to?

[ Parent | on HN ]

Re:Ask HN: Is machine learning worth learning for hobbyists/... by kace91 on Friday May 04, 2018 @05:14PM (#16998414)

> Do you have particular application areas or problems you want to apply ML to?

Not particularly, no. I've spent a ton of time reading about the math behind it and I feel as if I had been reading about functional programming or OOP without actually writing a single line of code... So I'm basically looking to get the practical approach, getting my hands dirty so to speak.

[ Parent | on HN ]