Why train when you can optimize?

Re:Why train when you can optimize? by em500 on Saturday April 30, 2022 @04:57AM (#31214469)

I have the creeping feeling that soon the field is going to reinvent all of Fourier analysis from scratch.

[ Parent | on HN ]

Re:Why train when you can optimize? by orbifold on Saturday April 30, 2022 @08:27AM (#31215506)

It will be called „Neural Harmonic Analysis“, it will cite one paper by a Russian and otherwise ignore any prior work which didn’t include the word neural network.

[ Parent | on HN ]

Re:Why train when you can optimize? by srean on Saturday April 30, 2022 @05:01PM (#31219321)

Its sad that this is not far from the truth

[ Parent | on HN ]

Re:Why train when you can optimize? by guidopallemans on Saturday April 30, 2022 @10:43AM (#31216440)

wavenet and transformer models already come dangerously close

[ Parent | on HN ]