{
  "aliases": null,
  "backlinks": [
    {
      "field": "defines",
      "target": "G2XY7J2Z5Q"
    }
  ],
  "body": "\n## Summary\n\nA Bayesian network is a [[graphical model|Q3FQAD1BXG]] on a directed acyclic graph.\nThe joint distribution is the product of the conditional distributions of each variable given its parents in the graph.\nThe arrows can often be read as direct influences, which makes Bayesian networks a common language for reasoning under uncertainty and for [[causal inference|V3QJFN5800]].\nEfficient algorithms compute conditional probabilities in networks with sparse graphs.\n\n## Explanations\n\n### L1 human\n\nRain makes the grass wet, and so does the sprinkler; rain also makes it less likely that the sprinkler is on.\nDraw an arrow from each cause to each thing it directly affects, with no loops of arrows.\nThen give, for each variable, its probabilities for every combination of its causes.\nThese small tables together fix the probability of every full scenario, as their product.\n",
  "commit": "ff8a40749dc16545e3d2fc637f6b0196e81d0bfa",
  "front": {
    "kind": "concept",
    "msc": [
      "62H22",
      "68T37"
    ],
    "name": "Bayesian network",
    "same_as": {
      "wikidata": "Q812540",
      "wikipedia": "Bayesian network"
    },
    "sources": [
      {
        "url": "https://en.wikipedia.org/wiki/Bayesian_network"
      }
    ],
    "specializes": [
      "Q3FQAD1BXG"
    ],
    "tag": "21JT983G60"
  },
  "kind": "concept",
  "link": "https://tamnd.github.io/math2/node/21JT983G60/",
  "links": [
    {
      "field": "specializes",
      "target": "Q3FQAD1BXG"
    }
  ],
  "markdown": "https://tamnd.github.io/math2/node/21JT983G60.md",
  "msc": [
    "62H22",
    "68T37"
  ],
  "name": "Bayesian network",
  "prov": null,
  "role": "",
  "source": "https://github.com/tamnd/math2/blob/main/nodes/21J/21JT983G60.md",
  "status": null,
  "tag": "21JT983G60",
  "uri": "m2://21JT983G60",
  "url": "https://tamnd.github.io/math2/wiki/bayesian-network/",
  "writing": {
    "tag": "21JT983G60",
    "kind": "concept",
    "level": "W0",
    "next": [
      {
        "what": "an inventory row",
        "note": "the row of the inventory that the node accounts for",
        "have": 0,
        "want": 1
      },
      {
        "what": "a source with a locator",
        "have": 0,
        "want": 1
      }
    ]
  }
}