ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-GM-012

Latent Diffusion

Running diffusion in a learned compressed latent space rather than pixel space.

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

Why it matters

The learner can explain why diffusing in an autoencoder's latent space reduces cost and name what the autoencoder's quality limits.

The route to this topic

Route AIML-GM-012
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 k-Means Complex Numbers Density Estimation: Histograms and Kernels Scores and Logits Loss and Fitting: Squared Error Basic Ratios Unit Circle The Artificial Neuron Linear Regression II: Least Squares Fitting Objective Functions and Empirical Risk Polynomial Functions Activation Functions Principal Component Analysis Likelihood Intuitive Limits Continuity Definition of the Derivative Differentiation Rules The Multilayer Perceptron Latent Representations Maximum Likelihood Estimation Bayesian Reasoning Chain Rule Antiderivatives & Indefinite Integrals What Generative Models Learn Forward Propagation Mixture Models Intuition Derivatives of Transcendental Functions Riemann Sums & Definite Integral Computational Graphs Expectation-Maximization Fundamental Theorem of Calculus The Chain Rule in Neural Nets Integration by Parts Backpropagation Sample Spaces & Events Autoencoders Random Variables & Distributions Joint Distributions Entropy & Mutual Information The Multivariate Gaussian Variational Inference and the ELBO Variational Autoencoders Denoising Diffusion Models Latent Diffusion