Figure  ·  Model architecture

The architecture of a multi‑layer GNMM

Layer indices run 1 → … → L from input to output  |  click any node to trace its signal path

Click a node on the canvas to trace its connections  ·  click an empty area or "All" to reset

FIGURE   The architecture of a multi-layer GNMM. The output μ_i^b depends on inputs x_i, weights w^(l), and biases d^(l) through a series of nested nonlinear activation functions g(·) for layers l = 1, …, L. The linear predictor for the random effects z_i^Tb_i is included in the final layer of the network.