Discover published sets by community

A computer vision program created by Google that uses a convolutional neural network to find and enhance patterns in images, creating a dream-like hallucinogenic appearance, such as turning landscapes into psychedelic patterns.

A class of AI algorithms used in unsupervised machine learning, implemented by a system of two neural networks competing against each other in a game. For example, GANs can generate realistic images that are indistinguishable from real photos.

A generative statistical model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar. For example, LDA can be used for topic discovery within a large set of text documents.

A type of model that relies on self-attention mechanisms to weigh the significance of each part of the input data differently. For example, transformers are the basis for language models like GPT-3, which can generate human-like text.

An extension of autoencoders that generates new instances that are similar to the input data. VAEs can be used to generate new faces or other complex data structures.

A type of neural network used to learn efficient codings of unlabeled data. An example use of autoencoders is dimensionality reduction, such as compressing images.

A stochastic neural network that can learn a probability distribution over its set of inputs. For instance, RBMs can be used for dimensionality reduction, feature learning, and topic modeling.