Models & Architecture
Autoencoder
A network that learns to compress data into a compact code and reconstruct it, useful for denoising and finding structure.
An autoencoder is trained to copy its input to its output through a narrow middle layer, which forces it to learn an efficient compressed representation of the data. That bottleneck code captures the essential structure, making autoencoders handy for compression, denoising, anomaly detection, and learning features without labels. Variants like the variational autoencoder can also generate new data.
Reference: Wikipedia: Autoencoder
Related terms
Embedding
A way of turning words, images, or other data into lists of numbers that capture their meaning, so a computer can compare them.
Unsupervised Learning
Training a model on data with no labels, so it has to find structure and patterns on its own.
Neural Network
A model loosely inspired by the brain, built from layers of simple units that each pass signals to the next.
Diffusion Model
A type of generative model, common in image tools, that creates content by starting from noise and gradually refining it.