How design a autoencoder architecture


I would like to build an autoencoder (CNN) to learn a representation of my data.

I never built such a network and I have some experience in supervised learning (classification).

I would like to know if some good practices in training a classifier is also right for an autoencoder:

  1. Does reference architecture exists like ResNet/Inception or something? If not, should I design manually layers?

  2. Does transfer learning/fine tuning works for autoencoder (or is it better to train from scratch)?


Posted 2018-09-10T16:10:38.060

Reputation: 378

second result on google:

– Mohammad Athar – 2018-09-10T16:26:04.583

Try reading the Keras blog! – Aditya – 2018-09-11T02:10:25.480



Yes, there are open source examples. Take a look at here and here. About your second question, yes. There are numerous studies. For instance, take a look at Supervised Representation Learning: Transfer Learning with Deep Autoencoders.


Posted 2018-09-10T16:10:38.060

Reputation: 12 077