a lot of the complicated stuff turned out not to be very useful or important. a few random examples: graphical models, variational autoencoders, RNN/LSTM, anything bayesian
Complicated ML Techniques Often Prove Less Useful Than Expected
By
–
By
–
a lot of the complicated stuff turned out not to be very useful or important. a few random examples: graphical models, variational autoencoders, RNN/LSTM, anything bayesian