# ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification

arXiv: https://arxiv.org/abs/2609.33967 · HTML: https://mlsanity.com/paper/2609.33967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search](https://mlsanity.com/paper/2007.10396/) (2020)
- [EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces](https://mlsanity.com/paper/2006.00622/) (2020)
- [Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016](https://mlsanity.com/paper/2004.06286/) (2020)
- [FBCNet: A Multi-view Convolutional Neural Network for Brain-Computer Interface](https://mlsanity.com/paper/2104.01233/) (2021)
- [EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification](https://mlsanity.com/paper/2101.10932/) (2021)
- [Inter-subject Deep Transfer Learning for Motor Imagery EEG Decoding](https://mlsanity.com/paper/2103.05351/) (2021)

## Abstract (arXiv)

Practical assistive and rehabilitative brain--computer interfaces require subject-independent motor-imagery EEG (MI-EEG) decoders that generalize to new users under limited target-user data and constrained compute. However, held-out-subject performance can be overstated when test-subject information influences preprocessing, model selection, or ensemble selection. We present textitThinkNet, a validation-controlled framework that combines train-only normalization, validation-guided evolutionary search, and validation-gated inference to identify compact decoders and inference policies for held-out subjects. We evaluate four-class BCI Competition IV-2a (session T) decoding with nine Leave-One-Subject-Out (LOSO) folds, three seeds, seven fixed decoder entries, and a broader search over ten representative decoder families; the held-out subject is never used for normalization, hyperparameter, architecture, or ensemble-policy selection. In the fixed benchmark, the validation-selected compact decoder achieved 44.35±15.41% accuracy with 4.9K parameters, 19 KB FP32 weights, and 0.99 ms batch-1 Orin CUDA inference. Across the broader search, compact models (≤25K parameters) achieved higher mean held-out accuracy than mid-size and large alternatives after selected retraining (40.10% vs. 35.09% and 34.78%). Validation-gated ensembling improved over validation-selected single-model inference, reaching 43.98±16.25% in the fixed benchmark and 43.31±15.88% for the compact six-family ensemble. A non-deployable oracle analysis revealed a 6.1-point family-selection gap and near-zero validation--test correlation, showing that validation reliability remains a key bottleneck under subject shift. Thus, ThinkNet is a validation-controlled framework for compact MI-EEG model and inference-policy selection, rather than a single-architecture benchmark.