Educational Implementation · Python
cde
Compiled Domain Expertise (CDE) compiles bounded AI reasoning into a static, language-agnostic Domain Instruction Set. Using an hourglass architecture, it replaces runtime neural nets with a deterministic, sub-megabyte relational graph delivering exact attribution, loud syntax checks, and microsecond execution on standard CPUs.
What it is
The repository presents the Compiled Domain Expertise (CDE) framework and Quantized Semantic Bottleneck Architecture (QSBA) as a specification for compiling domain expertise into deterministic instruction sets. It includes a reference implementation in the form of an Algebra EKC Workbench (backend and frontend) and extensive educational documentation.
Where it counts
- Machine Learning80%
- NLP & LLMs70%
- Data Science40%
- MLOps30%
- AI Agents20%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the Machine Learning board
Whole board- 18, shared rankrl-livive-netML Application · JavaScript58.6AdvancedJarad PeckenpaughMachine Learning
- 21LeNet_5-from-scratchArchitecture Reimplementation · Jupyter Notebook57.7ImplementationPop AlexandruMachine Learning
- 22, shared rankfresta-edgeML Application · Python57.4ImplementationTiago SantosMachine Learning
- 22, shared rankmines-livive-netTraining Experiment · JavaScript57.4ImplementationJarad PeckenpaughMachine Learning
- 22, shared rankcdeEducational Implementation · Python57.4ImplementationJarad PeckenpaughMachine Learning
