Batch Inference Configuration

Batch inference processes complete trials offline. Use it for calibration, validation, model comparison, research studies, and quality review. Use Streaming Inference Configuration when predictions must update during a live trial.

When To Use Batch

Train or calibrate a model on labeled trials.
Evaluate held-out sessions or subjects.
Compare model families and hyperparameters.
Run preprocessing diagnostics before deployment.
Analyze confidence, entropy, accuracy, and ITR after a session.

Data Contracts

SDK	Typical Batch Shape	Notes
Python classifiers	`(n_trials, n_features)`	sklearn-compatible estimator API.
Python `BCIData` utilities	`(n_features, n_samples, n_trials)`	Used by lower-level inference helpers.
Julia `BCIData`	`(n_features, n_samples, n_trials)`	Labels are typically 1-indexed integers.

All batch workflows should use preprocessed features, not raw EEG.

Basic Pattern

Python
Julia

from nimbus_bci import NimbusLDA
from sklearn.model_selection import cross_val_score

X = load_features()  # (n_trials, n_features)
y = load_labels()

clf = NimbusLDA()
scores = cross_val_score(clf, X, y, cv=5)

clf.fit(X, y)
probabilities = clf.predict_proba(X)
predictions = clf.predict(X)

using NimbusSDK
using Statistics

features = load_features()  # (n_features, n_samples, n_trials)
labels = load_labels()

metadata = BCIMetadata(
    sampling_rate = 250.0,
    paradigm = :motor_imagery,
    feature_type = :csp,
    n_features = size(features, 1),
    n_classes = length(unique(labels)),
    chunk_size = nothing
)

data = BCIData(features, metadata, labels)
model = train_model(NimbusLDA, data; iterations=50)
results = predict_batch(model, data)

accuracy = mean(results.predictions .== labels)

Evaluation Checklist

Split by session or subject when testing generalization.
Estimate normalization parameters on training folds only.
Report accuracy with confidence and rejection rate.
Inspect posterior entropy for uncertain trials.
Compare against a simple NimbusLDA baseline before tuning.

Batch Diagnostics

Run diagnostics when batch accuracy is unexpectedly low:

report = diagnose_preprocessing(data)

if !isempty(report.errors)
    error("Invalid batch data: $(report.errors)")
end

Common issues include wrong feature shape, raw EEG passed as features, inconsistent label encoding, missing normalization, and mismatched model metadata.

Batch vs Streaming

Need	Use
Offline calibration	Batch
Cross-validation	Batch
Research analysis	Batch
Live feedback	Streaming
Chunk-by-chunk command updates	Streaming

Most production BCI systems use both: batch for calibration and validation, streaming for live operation.

Next Read

Feature Normalization

Keep train/test/deployment scales consistent.

Streaming Inference

Configure live chunk processing.

Basic Examples

Compact batch and streaming recipes.

Model Specification

Choose a model before evaluation.

​Batch Inference Configuration

​When To Use Batch

​Data Contracts

​Basic Pattern

​Evaluation Checklist

​Batch Diagnostics

​Batch vs Streaming

​Next Read