Struct BayesianNetwork 

pub struct BayesianNetwork {
    pub nodes: [BayesianNode; 32],
    pub num_nodes: usize,
}

Fields

nodes: [BayesianNode; 32]

num_nodes: usize

Implementations

impl BayesianNetwork

pub fn new() -> Self

pub fn add_node(&mut self, node: BayesianNode) -> Result<(), &'static str>

pub fn extract_weight(quin: &NQuin) -> f32

Extract probability encoded in the Quin’s metadata field (canonical truth-degree via the FrameLayout ABI — shared with fuzzy/stochastic).

pub fn update_beliefs(&self, target_id: u64) -> Option<f32>

Exact inference via variable enumeration. Fully zero-allocation, iteratively evaluates joint probability table on the stack. Max unobserved variables allowed is 16 to prevent excessive CPU loop blocking (O(2^N)).

pub fn markov_blanket(&self, node_id: u64, out: &mut [u64]) -> usize

The Markov blanket of node_id: its parents, its children, and its children’s OTHER parents (co-parents). Conditioned on its blanket a node is independent of all others — the locality used for rapid conditional-independence testing and Gibbs sampling. Writes the member ids into out, returns the count. Zero-heap.

pub fn gibbs_estimate( &self, target_id: u64, samples: u32, seed: u64, ) -> Option<f32>

Gibbs sampling (MCMC) estimate of P(target = true | evidence) — approximate inference for networks too large for exact enumeration. samples sweeps, seed for the PRNG. Each non-evidence variable is resampled from its Markov-blanket conditional. Zero-heap (bounded stack arrays). None if target_id is not in the network.