Generative adversarial networks
Генеративно-состязательные сети
2020-10-22
SCID: 54.1/wpc8k8ja
Discuss with AI
Deep generative modelsGenerative adversarial networksGenerative modelingHigh-resolution image generation
Figures from the paper
Abstract (AI)
Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distribution that generated them. Generative Adversarial Networks (GANs) are then able to generate more examples from the estimated probability distribution. Generative models based on deep learning are common, but GANs are among the most successful generative models (especially in terms of their ability to generate realistic high-resolution images). GANs have been successfully applied to a wide variety of tasks (mostly in research settings) but continue to present unique challenges and research opportunities because they are based on game theory while most other approaches to generative modeling are based on optimization.
Key Findings
1
GANs can generate realistic high-resolution images and are among the most successful deep-learning-based generative models for image synthesis.
2
GANs have been successfully applied to a wide variety of tasks, primarily in research settings.
3
GANs present unique challenges and research opportunities because they are based on game-theoretic training rather than standard optimization approaches.
4
Generative adversarial networks (GANs) are AI algorithms that learn the data-generating probability distribution from training examples to produce new samples.
Research Object
Generative adversarial networks (GANs)
Research Subject
Their capability as generative models to learn and approximate training data probability distributions and generate realistic high-resolution examples, including associated challenges from their game-theoretic training
Publication Details
Publication Date
2020-10-22
Journal
Publisher
ISSN
Cited by
18349
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai1
Cited by20
The rise of deep learning in drug discovery2018
Deep learning in cancer diagnosis, prognosis and treatment selection2021
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy2023
Retrieval-Augmented Generation for AI-Generated Content: A Survey2026
Generative artificial intelligence2023
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines2021
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT2021
Deep learning in the construction industry: A review of present status and future innovations2020
Physics-informed machine learning: A comprehensive review on applications in anomaly detection and condition monitoring2024
Six Human-Centered Artificial Intelligence Grand Challenges2023
Artificial intelligence and machine learning for medical imaging: A technology review2021
Generative artificial intelligence in innovation management: A preview of future research developments2024
Rechargeable Batteries of the Future—The State of the Art from a BATTERY 2030+ Perspective2021
A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment2023
A comprehensive review of model compression techniques in machine learning2024
Computational approaches to Explainable Artificial Intelligence: Advances in theory, applications and trends2023
Governance of Generative AI2025
Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects2023
Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities2024
Applications of machine learning in metabolomics: Disease modeling and classification2022