do autoencoders work well for non images?


I have a classification problem for which a feedforward, fully connected neural net works reasonably well (two classes, true positive and true negative rate close to 80%).

I want to get these rates to 90%, and more features is one of the catalysts for improvements I can think of.

Do autoencoders to learn additional, interesting features work well for problems that do not involve images?

Alejandro Simkievich

Posted 2016-01-31T19:09:31.433

Reputation: 404

Which programming language do you use? Did you have the code? If possible could you send to me, please? – Mohammad – 2016-08-30T15:03:57.933



Yes, but no-one can tell if they will work well for your problem, so just try it and see. Don't give up if it does not work at first, because training neural networks requires some practice; there are lots of parameters, and not every configuration will work well. Even the optimization algorithm is a hyperparameter.


Posted 2016-01-31T19:09:31.433

Reputation: 9 953

thanks a lot Emre, will go ahead and try. Any particular library you recommend? thanks again. – Alejandro Simkievich – 2016-01-31T23:02:25.627 – Emre – 2016-02-01T04:05:25.323

awesome! I have already used keras, will try out the autoencoder – Alejandro Simkievich – 2016-02-01T10:36:22.600