Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
2026-07-20 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors explored a new type of neural network called Differentiable Logic Gate Networks (Diff-Logic) that uses simple True/False operations instead of complex math. They tested these on brain signal data (EEG) for detecting dementia and recognizing emotions, comparing them to standard neural networks. Diff-Logic performed as well or better, used less memory, and ran faster on small, low-power devices. This makes Diff-Logic a promising option for running brain-computer interface tasks on portable hardware. The authors also shared their code for others to try.
EEGNeural NetworksDifferentiable Logic Gate NetworksBinary ClassificationEmotion RecognitionEdge DevicesFloating-point ArithmeticBitwise OperationsBrain-Computer InterfaceLatency
Authors
Shyamal Y. Dharia, Stephen D. Smith, Camilo E. Valderrama
Abstract
Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native alternative that compiles models into pure Boolean circuits executable via bitwise CPU operations. Through rigorous iso-parameter experiments across four EEG datasets spanning two classification tasks, binary dementia detection and 3-class emotion recognition, we compared Diff-Logic against matched-capacity Multi-Layer Perceptron (MLP) and Binarized Neural Network (BNN) baselines at four complexity tiers (50k-500k parameters). On dementia screening, Diff-Logic achieved 80.2% Macro F1, outperforming the MLP baseline by 6.8%. On emotion recognition, the MLP retained a moderate performance advantage but incurred a 2.3$\times$ higher latency and 14$\times$ larger model size when deployed on a power-constrained (7W) Nvidia Jetson Orin Nano CPU (Single-core). Critically, Diff-Logic inference time remained nearly constant across a 10$\times$ increase in model scale, achieving a peak speedup of 2.9$\times$ over MLPs at the largest complexity tier. Our results establish logic-based neural architectures as a practical paradigm for resource-constrained brain-computer interfaces, achieving competitive or superior performance while natively satisfying the latency and memory constraints of portable edge deployment. Code is available on GitHub: https://github.com/Shyamal-Dharia/eeg-difflogic