Re:Machine Learning 101 slidedeck: 2 years of headbanging, s...
by fnl on Friday December 15, 2017 @09:20AM
(#15931935)
I work with language, not images. There, clever feature engineering isn't just better, it's essential to get anything that is production worthy. In fact, it will even be embedded in some expert system process if your system needs to understand very complex relationships. AI around the corner my ass... :-)
Re:Machine Learning 101 slidedeck: 2 years of headbanging, s...
by agibsonccc on Tuesday December 19, 2017 @05:47AM
(#15959274)
Agreed :). Workflow matters a lot more than the hype Sandhill road and google's marketing team are perpetuating. Good on you for making it work in the real world for something outside of vision/speech!
I guess what I wanted to do was add a bit of nuance. It can help reduce the amount of feature engineering needed. Of course you still need a baseline representation though. More feature engineering also doesn't hurt. I always think of deep learning in the time series context as a neat SVM kernel with some compression built in. With the right tuning it can give you a better representation which you can use with clustering and whatever else you'd like.