BFS, DFS, shortest paths, and common state modeling patterns.

Convolution, pooling, normalization, residual connections, and visual intuition.

Self-attention, positional encoding, multi-head attention, and vision transformer vocabulary.

Layered models, TCP/IP, HTTP, DNS, congestion control, and common interview topics.

Vectors, matrices, eigenvalues, SVD, and how they appear in model training.

Branch naming, commit scope, reproducible experiment snapshots, and documentation habits.

NumPy arrays, plotting, environment management, and simple packaging practices.

A repeatable structure for reading papers without losing the central question.