Deep Learning · Module 9
Answers and explanations · A tiny convolutional network you can account for
Compare these references after your own attempt. You can read them at any time; they do not record a live model or vendor run.
Deep Learning · Module 9
Compare these references after your own attempt. You can read them at any time; they do not record a live model or vendor run.
9A. Vertical center-column patch dotted with horizontal center-row kernel gives 1, at their intersection. Dotted with the vertical kernel gives 3. No kernel flip is applied in PyTorch's cross-correlation operation.
9B. No-padding convolution gives [B,4,6,6]; 2×2 pooling gives [B,4,3,3]; flatten gives [B,36]. Replace the head with Linear(36,2). Keeping Linear(64,2) would violate the matrix-multiplication contract.
9C. Horizontal flip preserves orientation and is label-preserving. A 90-degree rotation changes horizontal to vertical or vice versa, so the label must change. Added noise preserves the underlying orientation if it models plausible measurement noise and does not destroy the signal; its suitability is assumption-dependent.