Draw the weights and biases of f(x) = W2 φ(W1 x + b1) + b2 from N(0, α1²), N(0, β1²), N(0, α2²), N(0, β2²) and plot the resulting random functions. α1 makes the steps steeper, β1 moves their centres away from the origin, α2 scales the vertical range; with ReLU units and no biases the scales only rescale the output. The dashed band is plus and minus two exact prior standard deviations.
Ten functions are drawn with the demo kit's seeded generator; the table uses 400 further draws. The exact variance is H α2² E[φ(u)²] + β2² with u ~ N(0, α1²x² + β1²). The fraction of units whose step centre −b/w lies in [−1, 1] is (2/π) arctan(α1/β1).
code/ch17_bayesian_neural_networks.py (mlp_prior_functions, prior_output_variance, fig_17_1); Figure 17.1 in the code index.