EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks

A vast majority of spiking neural networks (SNNs) are trained based on inductive biases that are not necessarily a good fit for several critical tasks that require low-latency and power efficiency. Inferring brain behavior based on the associated electroenchephalography (EEG) signals is an example of how networks training and inference efficiency can be heavily impacted by learning spatio-temporal dependencies. Up to now, SNNs rely solely on general inductive biases to model the dynamic relations between different data streams. Here, we propose a graph spiking neural network architecture for multi-channel EEG classification (EEGSN) that learns the dynamic relational information present in the distributed EEG sensors. Our method reduced the inference computational complexity by $\times 20$ compared to the state-of-the-art SNNs, while achieved comparable accuracy on motor execution classification tasks. Overall, our work provides a framework for interpretable and efficient training of graph spiking networks that are suitable for low-latency and low-power real-time applications.

[1]  Liping Liu,et al.  Interpretable Node Representation with Attribute Decoding , 2022, Trans. Mach. Learn. Res..

[2]  G. R. Pedrollo,et al.  Spiking Neural Networks Diagnosis of ADHD subtypes through EEG Signals Evaluation , 2022, 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[3]  M. Sawan,et al.  Intelligent Classification Technique of Hand Motor Imagery Using EEG Beta Rebound Follow-Up Pattern , 2022, Biosensors.

[4]  Santosh K. Vishwakarma,et al.  Analysis of brain signal processing and real-time EEG signal enhancement , 2022, Multimedia Tools and Applications.

[5]  Ioannis E. Polykretis,et al.  A Spiking Neural Network Mimics the Oculomotor System to Control a Biomimetic Robotic Head Without Learning on a Neuromorphic Hardware , 2022, IEEE Transactions on Medical Robotics and Bionics.

[6]  Bo Zhang,et al.  CAttSleepNet: Automatic End-to-End Sleep Staging Using Attention-Based Deep Neural Networks on Single-Channel EEG , 2022, International journal of environmental research and public health.

[7]  Jiuwen Cao,et al.  3D residual-attention-deep-network-based childhood epilepsy syndrome classification , 2022, Knowl. Based Syst..

[8]  Xiang Li,et al.  EEG Based Emotion Recognition: A Tutorial and Review , 2022, ACM Comput. Surv..

[9]  Shanjida Khan Maliha,et al.  Grasp-and-Lift Detection from EEG Signal Using Convolutional Neural Network , 2022, 2022 International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE).

[10]  Guoxia Zou.  The Recognition of Action Idea EEG with Deep Learning , 2022, Complex..

[11]  K. Michmizos,et al.  A neurophysiologically interpretable deep neural network predicts complex movement components from brain activity , 2022, Scientific reports.

[12]  Rakhi Chakraborty,et al.  A Deep Learning-Based Comparative Study to Track Mental Depression from EEG Data , 2022, Neuroscience Informatics.

[13]  J. Sarnthein,et al.  A neuromorphic spiking neural network detects epileptic high frequency oscillations in the scalp EEG , 2021, Scientific Reports.

[14]  Christopher A. R. Chapman,et al.  Mind the gap: State-of-the-art technologies and applications for EEG-based brain–computer interfaces , 2021, APL bioengineering.

[15]  Lei Deng,et al.  Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning , 2021, IJCAI.

[16]  Z. Zhang,et al.  Classification of Motor Imagery EEG Based on Time-Domain and Frequency-Domain Dual-Stream Convolutional Neural Network , 2021 .

[17]  Neelesh Kumar,et al.  Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control , 2020, CoRL.

[18]  Yunhao Liu,et al.  Making Sense of Spatio-Temporal Preserving Representations for EEG-Based Human Intention Recognition , 2020, IEEE Transactions on Cybernetics.

[19]  K. Michmizos,et al.  Reinforcement co-Learning of Deep and Spiking Neural Networks for Energy-Efficient Mapless Navigation with Neuromorphic Hardware , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Tao Yin,et al.  Deep Learning Solutions for Motor Imagery Classification: A Comparison Study , 2020, 2020 8th International Winter Conference on Brain-Computer Interface (BCI).

[21]  Juan Humberto Sossa Azuela,et al.  Spiking Neural Networks applied to the classification of motor tasks in EEG signals. , 2020, Neural networks : the official journal of the International Neural Network Society.

[22]  Kostis P. Michmizos,et al.  Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAM , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[24]  Hong Wang,et al.  Loihi: A Neuromorphic Manycore Processor with On-Chip Learning , 2018, IEEE Micro.

[25]  Lina Yao,et al.  Cascade and Parallel Convolutional Recurrent Neural Networks on EEG-based Intention Recognition for Brain Computer Interface , 2017, AAAI.

[26]  Lei Deng,et al.  Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks , 2017, Front. Neurosci..

[27]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[28]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[29]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[30]  B. Meffert,et al.  EEG artifact elimination by extraction of ICA-component features using image processing algorithms , 2015, Journal of Neuroscience Methods.

[31]  Wulfram Gerstner,et al.  Neuronal Dynamics: From Single Neurons To Networks And Models Of Cognition , 2014 .

[32]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[33]  L. F Abbott,et al.  Lapicque’s introduction of the integrate-and-fire model neuron (1907) , 1999, Brain Research Bulletin.

[34]  K. Michmizos,et al.  Decoding EEG With Spiking Neural Networks on Neuromorphic Hardware , 2022, Trans. Mach. Learn. Res..

[35]  Shaohua Teng,et al.  A Multi-Dimensional Graph Convolution Network for EEG Emotion Recognition , 2022, IEEE Transactions on Instrumentation and Measurement.

[36]  Huan Liu,et al.  EEG-based Emotion Recognition with Emotion Localization via Hierarchical Self-Attention , 2022, IEEE Transactions on Affective Computing.