When Not to Use Deep Learning

hyperparameter.space

This illuminating post first does away with a number of misconceptions outsiders often have about deep learning of which typical straw men about when not to use deep learning are born (e.g. not enough data). Some real reasons cited include not having the necessary level of commitment to bear the substantial computational cost and time investments and the need to interpretability (especially for causal models). 

Read more...
Linkedin

Want to receive more content like this in your inbox?