ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-GM-011

Conditioning and Guidance

Steering generation with class labels or text: classifier guidance and classifier-free guidance.

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

Why it matters

The learner can vary the guidance scale and explain the trade-off between prompt adherence and sample diversity.

The route to this topic

Route AIML-GM-011
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 Unit Circle The Artificial Neuron Linear Regression II: Least Squares Fitting Polynomial Functions Activation Functions Principal Component Analysis Intuitive Limits Continuity Definition of the Derivative Differentiation Rules The Multilayer Perceptron Latent Representations Chain Rule Antiderivatives & Indefinite Integrals What Generative Models Learn Forward Propagation Derivatives of Transcendental Functions Riemann Sums & Definite Integral Computational Graphs Fundamental Theorem of Calculus The Chain Rule in Neural Nets Integration by Parts Backpropagation Sample Spaces & Events Random Variables & Distributions Joint Distributions The Multivariate Gaussian Denoising Diffusion Models Conditioning and Guidance