# Bayesian network A Bayesian network is a probabilistic graphical model that represents a set of variables and their conditional dependencies as a [[Directed_acyclic_graph|directed acyclic graph]]. Each node carries a conditional probability distribution given its parents, and the graph's structure encodes which variables are independent of which others once their parents are known, letting a large joint distribution factor into small, local pieces. ## Microsim — queued <p class="wt-pending"><strong>Microsim/diagram layer in the draft queue.</strong> Troy is building the interactive station for this concept by hand; the sourced overview below is complete and citable now.</p> ## Overview Because the graph is directed and acyclic, evidence entered at any node propagates through the network in both directions — diagnostic reasoning runs from effect back to cause, predictive reasoning runs from cause forward to effect. This dual-direction inference is what makes Bayesian networks useful for medical diagnosis, spam filtering, and decision support, and it is the same graphical machinery that a probabilistic [[Causal_model|causal model]] leans on to keep its assumptions explicit. **On the spine:** [[Causal_model]] · [[Directed_acyclic_graph]] · [[Causal_loop_diagram]] · [[Network_theory]] · [[Systems_theory]]. ## Wikipedia : Wikitube **Strict pair:** [Wikipedia](https://en.wikipedia.org/wiki/Bayesian_network) : [Wikitube](https://en.wikitube.io/wiki/Bayesian_network) ## Previous hub tags Hubs: `Systems`. Portals: [[PORTAL_Causal_loop_diagram]]. --- *Repopulated 2026-08-05 · text transfer · 0 deletions.*