Deep Learning
An autoencoder is a neural network that automatically learns by using its inputs as the expected output.
True
Proposed by @svpino
Card 1 of 259. Answer: True
True
Proposed by @svpino
Card 1 of 259. Answer: True
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.
True. An autoencoder is a neural network trained to reproduce its input at its output, so each input is its own target and no labels are needed. An encoder compresses x into a smaller code z, a decoder rebuilds an approximation x̂, and training minimizes a reconstruction loss such as the mean squared error between x and x̂.
Example: a 28 × 28 MNIST digit has 784 pixel values. An encoder might map them through layers of 256 and 64 units to a 32-number code, and a mirror-image decoder maps it back. The code is 24.5 times smaller than the image, so the network has to learn which features summarize a digit instead of copying pixels.
Without a bottleneck or another constraint, it can just learn the identity function. Denoising autoencoders corrupt the input and keep the clean original as the target. Uses include dimensionality reduction and anomaly detection, where high reconstruction error flags unusual inputs. Because the targets come from the data itself, autoencoders count as unsupervised or self-supervised.