Three networks on the same rings. Linear depth adds nothing; ReLU depth does.
Proof: W₅·W₄·W₃·W₂·W₁ = one 2→1 matrix
Multiplying the five weight matrices gives a single affine map. Running every point through it reproduces the 5-layer model exactly, because it is the same function.
collapsed weights (w₁, w₂ · bias)
—