proomt

Search

Search posts, papers, and topics

Hall of Fame

Hall of FameIan J. Goodfellow et al.201420 min readpaperadvanced

Generative Adversarial Nets

Read on arxiv.org

Summary

This paper introduces Generative Adversarial Nets (GANs), a novel framework for training generative models. It pits a generator (G) against a discriminator (D) in a minimax game, where G tries to produce data that D cannot distinguish from real data, and D tries to correctly classify real vs. generated samples.

  • GANs train a generator and a discriminator simultaneously in an adversarial minimax game.
  • The generator aims to produce data indistinguishable from real data, while the discriminator aims to correctly classify real vs. generated.
  • Unlike prior generative models, GANs do not require Markov chains or unrolled approximate inference for training or sampling.
  • Both models (G and D) can be trained using backpropagation, typically implemented with multilayer perceptrons.

This paper introduced a fundamentally new and highly influential approach to generative modeling, enabling significant advancements in realistic data synthesis across various domains.

10/10
machine learningdeep learninggenerative aineural networksganunsupervised learning

Related reading

  1. Deep Residual Learning for Image Recognition

    The paper proposes reformulating deep layers as residual functions with identity shortcut connections, making it easy to train networks far deeper than before. Using this design, a 152‑layer ResNet achieved 3.57% top‑5 error on ImageNet, winning ILSVRC 2015.

    Hall of Famearxiv.org42 minpaper

  4. Adam: A Method for Stochastic Optimization

    This paper introduces Adam, a first-order gradient-based optimization algorithm that adaptively estimates first and second moments of gradients. It computes individual learning rates for different parameters, making it efficient and robust for large-scale, high-dimensional machine learning problems with noisy or sparse gradients.

    Hall of Famearxiv.org32 minpaper

  5. ImageNet Classification with Deep Convolutional Neural Networks

    AlexNet introduced a deep convolutional network with ReLU activations, dropout regularization, and multi‑GPU training, achieving 15.3% top‑5 error on ImageNet 2012, far surpassing prior results. The paper demonstrated that large‑scale CNNs are feasible and set the foundation for modern deep vision.

    Hall of Famenips.cc24 minpaper