Not to be confused with Adversarial machine learning.
Part of a series on
Machine learning and data mining
Paradigms
Supervised learning
Unsupervised learning
Online learning
Batch learning
Meta-learning
Semi-supervised learning
Self-supervised learning
Reinforcement learning
Curriculum learning
Rule-based learning
Quantum machine learning
Problems
Classification
Generative modeling
Regression
Clustering
Dimensionality reduction
Density estimation
Anomaly detection
Data cleaning
AutoML
Association rules
Semantic analysis
Structured prediction
Feature engineering
Feature learning
Learning to rank
Grammar induction
Ontology learning
Multimodal learning
Supervised learning (classification • regression)
Apprenticeship learning
Decision trees
Ensembles
Bagging
Boosting
Random forest
k-NN
Linear regression
Naive Bayes
Artificial neural networks
Logistic regression
Perceptron
Relevance vector machine (RVM)
Support vector machine (SVM)
Clustering
BIRCH
CURE
Hierarchical
k-means
Fuzzy
Expectation–maximization (EM)
DBSCAN
OPTICS
Mean shift
Dimensionality reduction
Factor analysis
CCA
ICA
LDA
NMF
PCA
PGD
t-SNE
SDL
Structured prediction
Graphical models
Bayes net
Conditional random field
Hidden Markov
Anomaly detection
RANSAC
k-NN
Local outlier factor
Isolation forest
Artificial neural network
Autoencoder
Cognitive computing
Deep learning
DeepDream
Feedforward neural network
Kolmogorov–Arnold Network
Recurrent neural network
LSTM
GRU
ESN
reservoir computing
Restricted Boltzmann machine
GAN
Diffusion model
SOM
Convolutional neural network
U-Net
Transformer
Vision
Mamba
Spiking neural network
Memtransistor
Electrochemical RAM (ECRAM)
Reinforcement learning
Q-learning
SARSA
Temporal difference (TD)
Multi-agent
Self-play
Learning with humans
Active learning
Crowdsourcing
Human-in-the-loop
RLHF
Model diagnostics
Coefficient of determination
Confusion matrix
Learning curve
ROC curve
Mathematical foundations
Kernel machines
Bias–variance tradeoff
Computational learning theory
Empirical risk minimization
Occam learning
PAC learning
Statistical learning
VC theory
Machine-learning venues
ECML PKDD
NeurIPS
ICML
ICLR
IJCAI
ML
JMLR
Related articles
Glossary of artificial intelligence
List of datasets for machine-learning research
List of datasets in computer vision and image processing
Outline of machine learning
v
t
e
A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative AI.[1][2] The concept was initially developed by Ian Goodfellow and his colleagues in June 2014.[3] In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss.
Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proved useful for semi-supervised learning,[4] fully supervised learning,[5] and reinforcement learning.[6]
The core idea of a GAN is based on the "indirect" training through the discriminator, another neural network that can tell how "realistic" the input seems, which itself is also being updated dynamically.[7] This means that the generator is not trained to minimize the distance to a specific image, but rather to fool the discriminator. This enables the model to learn in an unsupervised manner.
GANs are similar to mimicry in evolutionary biology, with an evolutionary arms race between both networks.
^"Generative AI and Future". November 15, 2022.
^"CSDL | IEEE Computer Society".
^Goodfellow, Ian; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua (2014). Generative Adversarial Nets(PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680.
^Salimans, Tim; Goodfellow, Ian; Zaremba, Wojciech; Cheung, Vicki; Radford, Alec; Chen, Xi (2016). "Improved Techniques for Training GANs". arXiv:1606.03498 [cs.LG].
^Isola, Phillip; Zhu, Jun-Yan; Zhou, Tinghui; Efros, Alexei (2017). "Image-to-Image Translation with Conditional Adversarial Nets". Computer Vision and Pattern Recognition.
^Ho, Jonathon; Ermon, Stefano (2016). "Generative Adversarial Imitation Learning". Advances in Neural Information Processing Systems. 29: 4565–4573. arXiv:1606.03476.
^"Vanilla GAN (GANs in computer vision: Introduction to generative learning)". theaisummer.com. AI Summer. April 10, 2020. Archived from the original on June 3, 2020. Retrieved September 20, 2020.
and 23 Related for: Generative adversarial network information
The Wasserstein GenerativeAdversarialNetwork (WGAN) is a variant of generativeadversarialnetwork (GAN) proposed in 2017 that aims to "improve the stability...
potential samples of input variables. Generativeadversarialnetworks are examples of this class of generative models, and are judged primarily by the...
variational autoencoder and generativeadversarialnetwork produced the first practical deep neural networks capable of learning generative models, as opposed...
StyleGAN is a generativeadversarialnetwork (GAN) introduced by Nvidia researchers in December 2018, and made source available in February 2019. StyleGAN...
nor used gradient descent." In 2014, this adversarial principle was used in a generativeadversarialnetwork (GAN) by Ian Goodfellow et al. Here the environmental...
figure's voice being used against them. This method uses a generativeadversarialnetwork (GAN), a deep machine learning technique where two machine learning...
testing environment or an artificial intelligence, for example a generativeadversarialnetwork. The designer learns to refine the program (usually involving...
Edmond de Belamy is a generativeadversarialnetwork (GAN) portrait painting constructed in 2018 by Paris-based arts-collective Obvious. Printed on canvas...
to the field of deep learning including the invention of the generativeadversarialnetwork (GAN). Goodfellow co-wrote, as the first author, the textbook...
not seem to apply in the adversarial context. Pattern recognition Fawkes (image cloaking software) Generativeadversarialnetwork Kianpour, Mazaher; Wen...
quantize a feature representation layer in the discriminator of Generativeadversarialnetworks. The feature quantization (FQ) technique performs implicit...
"Enhanced Deep Residual Networks for Single Image Super-Resolution". arXiv:1707.02921 [cs.CV]. "GenerativeAdversarialNetwork and Super Resolution GAN(SRGAN)"...
at Université de Montréal developed the generativeadversarialnetwork (GAN), a type of deep neural network capable of learning to mimic the statistical...
a generativeadversarialnetwork (GAN) by Ian Goodfellow et al. Here the environmental reaction is 1 or 0 depending on whether the first network's output...
and generativeadversarialnetworks to obtain hybrid models. Autoencoder Artificial neural network Deep learning Generativeadversarialnetwork Representation...
systems Generativeadversarialnetwork – Deep learning method Generative art – Art created by a set of rules, often using computers Generative artificial...
Retrieved 25 August 2017. "Yet Another Text Captcha Solver: A GenerativeAdversarialNetwork Based Approach" (PDF). 25th ACM Conference on Computer and Communications...
Elwes set out to "Queer the Dataset" through an open-sourced generativeadversarialnetwork (GAN). Elwes added a dataset of 1,000 photos of drag kings and...