Skip to main content

Module deep_fusion

Module deep_fusion 

Source
Expand description

Multi-layer fusion operator (Section 7, Paper 4).

Implements deep Bayesian fusion as a multi-layer network:

    l^(k) = g( l^(k-1) + sum_j logit(P_j^(k)) )
    P_final = sigmoid(l^(K))

The internal channel map keys per-document feature vectors. Each Layer variant updates that map, including signal, dense, convolutional, recurrent, normalization, attention, and graph-aware propagation / pooling layers.

Structs§

DeepFusionOperator

Enums§

AggregationKind
Gating
GlobalPoolMethod
Layer
PoolMethod