What is Autoencoder?
An autoencoder is a neural network that learns to compress input data into a smaller representation and then reconstruct the original data from that compressed form.
It consists of two main parts: an encoder that maps the input to a low-dimensional latent space, and a decoder that tries to rebuild the input from this compressed code. Training minimizes the difference between the original input and the reconstruction.
Because it learns without labels, an autoencoder discovers useful patterns in the data on its own. The bottleneck layer forces the network to capture only the most important features.
Common variants include denoising autoencoders that remove noise and variational autoencoders that add probabilistic structure to the latent space.
Example
A photo of a handwritten digit is fed into an autoencoder; the network compresses the 784-pixel image into a 32-number code and then reconstructs a clean version of the same digit from that code.
Why it matters
Autoencoders enable unsupervised feature learning and dimensionality reduction, powering applications such as anomaly detection, image denoising, and the foundation of modern generative models.
Frequently asked questions
PCA is a linear method while an autoencoder can learn non-linear transformations, often capturing more complex structure in the data.
Related terms
Unsupervised learning is a machine learning method that trains models on unlabeled data to find hidden patterns, structures, or relationships without any guidance on correct outputs.
A Variational Autoencoder (VAE) is a neural network that learns a compressed probabilistic representation of data and can generate new similar examples by sampling from that space. It combines autoencoders with variational inference to enable both reconstruction and generation.
An activation function is a mathematical operation applied to the output of a neuron in a neural network that decides whether the neuron should 'fire' and pass on a signal.
Backpropagation is an algorithm for training neural networks by calculating how much each weight contributed to the prediction error and adjusting those weights accordingly. It uses the chain rule to efficiently compute gradients of the loss function.
A Convolutional Neural Network (CNN) is a specialized type of deep neural network designed to process grid-like data such as images by automatically learning spatial patterns and features.
In deep learning, a decoder is a neural network module that converts an encoded representation (like a context vector or latent features) into a final output such as text, images, or sequences.