The problem
A Multi-Electrode Array holds a living culture whose behaviour is the object of study. Unlike an artificial network, you cannot read out its weights — the parameters are chemistry and morphology, not numbers in a file.
What you can observe is activity at each electrode, and what you can build on top of that is a model that predicts something about the culture. The explainability question is then: can the model be interrogated in ways that produce claims about the biology, not just about the model?
A single method will not do this. Electrode importance tells you where, rule extraction tells you under what conditions, counterfactuals tell you what would have to change, and spatial statistics tell you whether any of it is organised or coincidental. The framework exists because those are four different questions.
The five methods
1. Electrode importance — ANNIGMA
Ranks electrodes by the gain they contribute through a trained network's weights. Cheap to compute and stable, which makes it a good first pass over a 60-electrode array.
2. Electrode importance — permutation
Measures the performance drop when an electrode's signal is shuffled. Model-agnostic and grounded in the actual predictive contribution rather than the architecture. Running both matters: where the two rankings disagree is where something interesting is happening — typically correlated electrodes whose importance one method attributes and the other distributes.
3. Fuzzy rule extraction
Extracts human-readable IF-THEN rules describing the conditions under which the model predicts activity. This is the direct link to the spike detection work, where the rule base is the classifier rather than a summary of one.
4. Counterfactual explanations
Answers the question an importance score cannot: what minimal change to the input would flip the prediction? For a biocomputer this is the closest available analogue to an intervention — a hypothesis about which activity pattern is doing the causal work, stated precisely enough to be tested.
5. Spatial autocorrelation and hub detection
Moran's I quantifies whether activity is spatially clustered across the electrode grid or effectively random. Combined with NetworkX-based functional connectivity analysis, it identifies hub electrodes — sites that are disproportionately connected within the culture's functional network.
This is where the framework stops describing a model and starts describing biology. A hub electrode is a claim about the culture's organisation, and it is falsifiable.
hub electrodes highlighted, Moran's I annotated
Why combine them
Each method has a characteristic blind spot, and the blind spots do not overlap.
| Method | Answers | Blind to |
|---|---|---|
| ANNIGMA | Which electrodes carry gain | Correlated-feature redundancy |
| Permutation | Which electrodes the model needs | Interaction effects |
| Fuzzy rules | Under what conditions | Continuous magnitude |
| Counterfactuals | What would have to change | Global structure |
| Moran's I / hubs | How activity is organised | Predictive relevance |
Read together they triangulate. An electrode that ranks highly on both importance measures, appears in high-weight rules, and sits at a network hub is a genuine finding. One that ranks highly on a single measure is a lead.
Related work
- Interpretable spike detection — the classifier this framework interrogates, published at WCCI FUZZ-IEEE 2026.
- Neural Biocomputer Analysis Toolkit — the signal-processing layer beneath it: bandpass filtering, burst detection, connectivity matrices and raster plots.
- Interval Type-2 Fuzzy Classifier — modelling second-order uncertainty for biological variability.