MML-16-01: Neural Network Architecture: Composed Affine Transformations & Non-Linearities – Practice Quiz

Develop rigorous mathematical and geometric mastery of feedforward neural network architectures: multi-layer functional composition $f(\mathbf{x}) = (f_L \circ \dots \circ f_1)(\mathbf{x})$, matrix-vector and batched affine transformations, exact parameter counting, algebraic proofs of linear collapse in the absence of non-linearities, rank bottlenecks, coordinate warping for the non-separable XOR problem, and hyperplane arrangements partitioning input space into convex polytopes. Aligns with Prerequisites: Parts 02, 06; Cognitive Level: Tier 1–3.