> ML_ARCHITECTURE // GENERATIVE-ADVERSARIAL-NETWORK-GAN_v1.0
Generative Adversarial Network (DCGAN / StyleGAN / HiFi-GAN)
Minimax game-theoretic generative architecture pitting a generator network synthesizing samples against a discriminator network distinguishing real from synthetic distributions, capable of single-pass fast generation.
Deep Generative Modelsimageaudio
Back to All ArchitecturesArchitecture Overview
Minimax game-theoretic generative architecture pitting a generator network synthesizing samples against a discriminator network distinguishing real from synthetic distributions, capable of single-pass fast generation.
Implementing Libraries
Seminal Papers
Generative Adversarial Nets (GAN)Ian J. Goodfellow, Jean Pouget-Abadie (2014) · Advances in Neural Information Processing Systems (NeurIPS)
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech SynthesisJungil Kong, Jaehyeon Kim (2020) · Advances in Neural Information Processing Systems (NeurIPS)
Architectural Limitations & Constraints
- Requires compatible deep learning framework and hardware acceleration for efficient execution.