WikiWIKI Graph
Wiki
Reference handbooks — evergreen content updated continuously
Browse Documents
0 documentsRecently Updated
- Tokens and tokenizersDistinguishes characters, bytes, subwords, and integer token IDs, and explains BPE merge rules and subword tokenization pipelines.
- Pretraining, fine-tuning, and in-context learningDistinguishes gradient-based parameter updates in pretraining and fine-tuning from frozen-weight conditioning in in-context learning.
- Transfer learning and negative transferExplains how source data shifts target risk under a fixed learning algorithm and distinguishes parameter, feature, and instance transfer.
- Union-findMaintain a partition of disjoint sets using parent-pointer trees, union by size, and path compression in inverse-Ackermann amortized time.
- Dijkstra’s algorithmSettle the smallest tentative distance in a nonnegative-weight graph, relax outgoing edges, and understand priority-queue and negative-edge boundaries.
- Depth-first searchFollow one branch to completion before backtracking, preserve recursive discovery order with explicit stack frames, and apply the parenthesis theorem.
- Breadth-first searchExplore a graph layer by layer with a FIFO queue, preserve the two-level wavefront invariant, and compute minimum edge counts in unweighted graphs.
- Merge sortDivide an array into halves, merge sorted subranges in linear time, preserve stability on equal keys, and manage auxiliary buffer space.