Python implementation of the context tree weighting (CTW) method for sequential probability assignment.
-
Updated
Sep 1, 2022 - Python
Python implementation of the context tree weighting (CTW) method for sequential probability assignment.
A lossless compressor based on Context Tree Weighting
implementation of the CTW algorithm
Holonics: a mathematical, physical and computational framework grounded in the reality of difference. Exact arithmetic in Rust and CUDA, formal mathematics in Lean 4, and the HNN, a learning machine built from rings and helical contacts. Research in progress, shared openly.
Context Tree Weighting
An Information-Theoretic Approach to Word ordering and Morphosyntactic Information in Ancient Greek. Applying a CTW statistical model on Universal Depedencies
AIXI-derived algorithm playing pong with no prior knowledge
Finite-memory language modeling with context trees: CTW, GPT-2, and data-sparsity experiments
Python implementation of Context Tree Weighting (CTW) lossless compression.
Log-domain context-tree weighting with exact rational mixture checks, prequential prediction benchmarks, and a nonstationary stress test.
Local benchmark of agents on 20 frozen finite-state tasks with declared proxy vectors
Reproducibility bundle for 'Online Routing for Next-Action Prediction' (Langiu & Pilato): online routing over a classical + neural predictor pool; leave-one-user-out benchmark. DOI 10.5281/zenodo.20995956
To associate your repository with the context-tree-weighting topic, visit your repo's landing page and select "manage topics."