Vision & Multimodal Jun 2014

Generative Adversarial Networks

Ian J. Goodfellow et al. · NeurIPS 2014

arXiv:1406.2661

In short

Two networks train against each other: a generator tries to produce samples that look real, and a discriminator tries to tell them from training data. At equilibrium the generator reproduces the data distribution, and both are trained with plain backpropagation.

Why it matters

GANs launched the modern era of generated images and dominated image synthesis until diffusion arrived.

Read first

The 4 Field Guide ideas this paper leans on.

Neural Networks · Landmark Neural Network A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections. Vision & Multimodal · Reference Generator In GANs, the network that creates synthetic data attempting to fool the discriminator into thinking it's real. Vision & Multimodal · Reference Discriminator In GANs, the network that tries to distinguish between real and generated data, providing training signal to the generator. Vision & Multimodal · Standard Generative Adversarial Network A framework where two networks (generator and discriminator) compete, with the generator learning to create realistic data.

Starting from scratch? The full route 8 ideas · basics first

Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
Neural Network · read first ✓ understood
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.
Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
Training ✓ understood
The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.
Loss Function ✓ understood
A function that scores how wrong a model's prediction is as a single number, which training then works to make as small as possible.
Generative Adversarial Network · read first ✓ understood
A framework where two networks (generator and discriminator) compete, with the generator learning to create realistic data.
Generator · read first ✓ understood
In GANs, the network that creates synthetic data attempting to fool the discriminator into thinking it's real.
Discriminator · read first ✓ understood
In GANs, the network that tries to distinguish between real and generated data, providing training signal to the generator.

Nearby papers

Canon · 1958 The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain It is the first learning neural network: the idea that weights, not rules, should hold the knowledge starts here. Canon · 1986 Learning Representations by Back-Propagating Errors Backpropagation is how essentially every neural network, from LeNet to today’s LLMs, is trained. Canon · 1998 Gradient-Based Learning Applied to Document Recognition It is the blueprint for the convolutional network, the architecture that later cracked computer vision. Canon · 2015 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift It made very deep networks practical to train, and normalization layers became a standard part of the recipe.