What Does Autoencoder Mean?

An autoencoder (AE) is a specific kind of unsupervised artificial neural network that provides compression and other functionality in the field of machine learning. The specific use of the autoencoder is to use a feedforward approach to reconstitute an output from an input. The input is compressed and then sent to be decompressed as output, which is often similar to the original input. That is the nature of an autoencoder – that the similar inputs and outputs get measured and compared for execution results.


An autoencoder is also known as an autoassociator or diabolo network.

Techopedia Explains Autoencoder

An autoencoder has three essential parts: an encoder, a code and a decoder. The original data goes into a coded result, and the subsequent layers of the network expand it into a finished output. One way to understand autoencoders is to take a look at a “denoising” autoencoder. The denoising autoencoder uses original inputs along with a noisy input, to refine the output and rebuild something representing the original set of inputs. Autoencoders are helpful in image processing, classification and other aspects of machine learning.


Related Terms

Margaret Rouse

Margaret is an award-winning technical writer and teacher known for her ability to explain complex technical subjects to a non-technical business audience. Over the past twenty years, her IT definitions have been published by Que in an encyclopedia of technology terms and cited in articles by the New York Times, Time Magazine, USA Today, ZDNet, PC Magazine, and Discovery Magazine. She joined Techopedia in 2011. Margaret's idea of a fun day is helping IT and business professionals learn to speak each other’s highly specialized languages.