AI-ordlista
Den kompletta ordlistan över AI
Bayesian Networks
Directed graphical models representing conditional dependencies between variables through conditional probabilities.
Markov Random Fields
Undirected graphical models capturing symmetric dependencies between variables through local potentials.
Modèles de Markov Cachés
Modèles séquentiels stochastiques où les états cachés suivent une chaîne de Markov et génèrent des observations.
Belief Networks
Extensions of Bayesian networks with discrete and continuous variables, using conditional probability tables.
Conditional Random Fields
Undirected discriminative models for structured prediction, conditioned on observations
Boltzmann Machines
Undirected stochastic neural networks used for representation learning and sampling.
Exact Inference
Algorithms that compute exact probability distributions in graphical models through variable elimination or message passing.
Approximate Inference
Approximation methods like MCMC and sampling for inference in complex graphical models.
Parametric Learning
Estimation of conditional probability parameters in graphical models from observed data.
Structure Learning
Automatic determination of the graph structure (edges and nodes) from data.
Dynamic Graphical Models
Temporal extension of graphical models capturing evolving dependencies between variables over time.
Factorial Models
Compact representation of probability distributions via factorization into multiplicative local terms.