What label smoothing does: replaces one-hot [0,0,1,0] with [0.025, 0.025, 0.925, 0.025]

What calibration means: a model predicting 80% should be correct 80% of the time

Calibration: Model's predicted probabilities match actual outcomes' frequencies

What cutmix does: replaces a patch of one image with a patch from another

Patch-based image cutmix swaps image sections for data augmentation

A p-value < 0.05 means: if H₀ is true, this result has <5% probability

A p-value < 0.05 indicates a less than 5% chance of observing data as extreme as this if the null hypothesis is true

What denoising score matching does: learns to denoise, which equals learning the score

Denoising score matching learns to remove noise, enhancing signal representation and interpretation

Why L1 regularization produces sparse solutions — the diamond corners touch axes

L1 regularization promotes sparsity by penalizing non-zero coefficients, effectively driving some to zero

Why temperature T in softmax(x/T) controls entropy: T→0 is argmax, T→∞ is uniform

As T approaches zero, softmax becomes argmax, maximizing entropy; T→∞ yields uniform distribution, minimizing entropy