Models
This section is the registry of neural-network models used by πENABOL ablation experiments. Each model gets a stable ID so an experiment can be described as a composition of:
Dataset + Model + Training method + Precision map + Drift/corruption
Use model IDs in experiment trace blocks:
Model: MDL-DENSE1-LINEAR-NOBIAS-000
Model Tableβ
| Model ID | Name | Layers | Activation | Bias | Trainable Params | Status | Notes |
|---|---|---|---|---|---|---|---|
MDL-DENSE1-LINEAR-NOBIAS-000 | One Dense linear student, no bias | 1 Dense | None | No | 8 | Active | Used by EXP-000A and EXP-000B. |
ID Conventionβ
Use:
MDL-<ARCH>-<DETAIL>-<NUMBER>
Examples:
MDL-DENSE1-LINEAR-NOBIAS-000
MDL-DENSE2-RELU-BIAS-001
MDL-CNN-SMALL-010
Keep IDs stable once used in experiment documentation. If the architecture, activation, bias behavior, or layer naming changes in a way that affects results, create a new model ID.
Model Record Checklistβ
Each model page should define:
- ID and short name,
- layer sequence,
- stable layer names,
- forward equations,
- trainable parameters,
- expected input/output shapes,
- whether bias, activation, or normalization is enabled,
- code path used to instantiate it,
- caveats that affect interpretation.