ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-GM-004

Generative Adversarial Networks

A generator and a discriminator in a minimax game, and the instabilities (mode collapse, oscillation) that follow.

Difficulty
3 / 5
Importance
4 / 5
Study time
1–2 h
Kind of work
Mixed

Why it matters

The learner can trace a GAN's generator and discriminator updates on a 1D target and recognise mode collapse.

The route to this topic

Route AIML-GM-004
Natural Numbers What Is a Model? Variables & Constants Tasks: Regression, Classification, and Beyond Features and Targets Solving Linear Equations Function Notation & Composition Probabilistic Prediction Classification Framing Linear Regression I: Prediction and Residuals Complex Numbers Density Estimation: Histograms and Kernels Scores and Logits Loss and Fitting: Squared Error Basic Ratios The Artificial Neuron Linear Regression II: Least Squares Fitting Polynomial Functions Activation Functions Principal Component Analysis Definition of the Derivative Differentiation Rules The Multilayer Perceptron Latent Representations Chain Rule Forward Propagation What Generative Models Learn Computational Graphs The Chain Rule in Neural Nets Backpropagation Generative Adversarial Networks