Diagnose overfitting, DenseNet, preprocessing, CV

Define overfitting and propose three distinct mitigation techniques; for each, explain how it affects bias/variance and training dynamics. Describe DenseNet’s connectivity pattern versus ResNet, why it helps gradient flow and parameter efficiency, and when it can hurt. Given a medical‑imaging dataset with class imbalance and scanner drift, detail a leakage‑free preprocessing pipeline (normalization, augmentation, harmonization) and justify choices. List five common CNN hyperparameters and how you’d tune them efficiently (search space, schedulers, early stopping). Compare k‑fold, stratified, and nested cross‑validation; when is each necessary to avoid optimistic estimates?