Float16 vs bfloat16: bfloat16 has same exponent range as float32, less precision but more stable

Finite element method

Runge-Kutta method improves Euler by providing higher-order accuracy with k₁,k₂,k₃,k₄

arithmetic intensity is

Arithmetic intensity = FLOPs / Bytes accessed

Effect size

Cohen's D benchmarks: 0.2 = small, 0.5 = medium, 0.8 = large effect

BFS vs DFS: BFS finds shortest path in unweighted graphs, DFS uses less memory

BFS finds shortest path in unweighted graphs; DFS uses less memory

the L1 norm is not differentiable at zero

Absolute value's kink makes it non-differentiable at zero

BLEU vs ROUGE: BLEU measures precision of n-grams, ROUGE measures recall

BLEU measures precision of n-grams, ROUGE measures recall