How should we choose the dimensions of the encoding layer in auto-encoders?

Question

score 3 · Answer 1 · edited Dec 26 '19 at 15:31

3

The number of dimensions is a hyperparameter of your model, and you should do a hyperparameter search, like with any other parameters. There's also a tradeoff between dimension and training speed, so it should be small enough to be trainable in a reasonable time.

edited Dec 26 '19 at 15:31

nbro

40,472
12
105
192

answered Dec 28 '18 at 16:14

Konstantin Solomatov

298
2
10

How should we choose the dimensions of the encoding layer in auto-encoders?

1 Answers1