Autoencoder

**Definition:** An unsupervised learning technique where the machine learns patterns in unlabeled data sets, makes compressed representations and reconstructs the input as output at minimum loss of features from the input. Autoencoders are useful in denoising images, DIMENSIONALITY REDUCTION and feature extraction.

**Tree numbers:** - G17.035.250.500.250.250 - G17.035.250.500.750.500 - G17.035.297 - G17.485.500.250 - L01.224.050.375.530.250.250 - L01.224.050.375.530.750.500 - L01.224.050.375.605.500.250 - L01.224.050.395