An Online Learning Framework for Neural Decoding in Embedded Neuromodulation Systems

Abstract

Introduction:

Advancements in brain–computer interfaces (BCIs) have improved real-time neural signal decoding, enabling adaptive closed-loop neuromodulation. These systems dynamically adjust stimulation parameters based on neural biomarkers, enhancing treatment precision and adaptability. However, existing neuromodulation frameworks often depend on high-power computational platforms, limiting their feasibility for portable, real-time applications.

Methods:

We propose RONDO (Recursive Online Neural DecOding), a resource-efficient neural decoding framework that employs dynamic updating schemes in online learning with recurrent neural networks (RNNs). RONDO supports simple RNNs, long short-term memory networks, and gated recurrent units, allowing flexible adaptation to different signal type, accuracy, and real-time constraints.

Results:

Experimental results show that RONDO’s adaptive model updating improves neural decoding accuracy by 35% to 45% compared to offline learning. Additionally, RONDO operates within real-time constraints of neuroimaging devices without requiring cloud-based or high-performance computing. Its dynamic updating scheme ensures high accuracy with minimal updates, improving energy efficiency and robustness in resource-limited settings.

Conclusions:

RONDO presents a scalable, adaptive, and energy-efficient solution for real-time closed-loop neuromodulation, eliminating reliance on cloud computing. Its flexibility makes it a promising tool for clinical and research applications, advancing personalized neurostimulation and adaptive BCIs.

Impact Statement

This research introduces RONDO (Recursive Online Neural DecOding), a novel framework for real-time, resource-efficient neural decoding in closed-loop neuromodulation and neurofeedback. By leveraging online learning with recurrent neural networks, RONDO enhances adaptability, accuracy, and energy efficiency, addressing key challenges in neurostimulation. Its ability to operate without dependency on cloud computing makes it ideal for portable, real-world applications. This work advances neural decoding technologies, contributing to more precise, personalized treatments for neurological disorders and expanding the potential of adaptive brain–computer interfaces in both clinical and research settings.

Keywords

embedded neuromodulation neural decoding RNN-based neural decoding

Get full access to this article

View all access options for this article.

References

Ahmadi

, Constandinou

, Bouganis

C-S

. Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning. J Neural Eng, 2021; 18(2):10.1088/1741–12552/abde8a.

Ajioka

, Nakai

, Yamashita

, et al. End-to-end deep learning approach to mouse behavior classification from cortex-wide calcium imaging. PLoS Comput Biol, 2024; 20(3):e1011074.

Azabou

, Arora

, Ganesh

, et al. A unified, scalable framework for neural population decoding. Adv Neural Inf Process Syst, 2024:36.

Barbera

, Liang

, Zhang

, et al. Spatially compact neural clusters in the dorsal striatum encode locomotion relevant information. Neuron, 2016; 92(1):202–213.

Basu

, Yousefi

, Crocker

, et al. Closed-loop enhancement and neural decoding of cognitive control in humans. Nat Biomed Eng, 2023; 7(4):576–588.

Bouthour

, Mégevand

, Donoghue

, et al. Biomarkers for closedloop deep brain stimulation in Parkinson disease and beyond. Nat Rev Neurol, 2019; 15(6):343–352.

Brandman

, Hosman

, Saab

, et al. Rapid calibration of an intracortical brain–computer interface for people with tetraplegia. J Neural Eng, 2018; 15(2):26007.

Chollet

, et al. (2015). Keras. Available from: https://github.Com/fchollet/keras

Dado

, Papale

, Lozano

, et al. Brain2GAN: Feature-disentangled neural coding of visual perception in the primate brain. BioRxiv, 2023:2023–2024.

10.

Dey

, Salem

. (2017). “Gate-Variants of Gated Recurrent Unit (GRU) neural networks”. In: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS). IEEE, pp. 1597–1600.

11.

Farshchian

, Gallego

, Cohen

, et al. Adversarial domain adaptation for stable brain-machine interfaces. arXiv Preprint arXi, 2018.

12.

Glaser

, Benjamin

, Chowdhury

, et al. Machine learning for neural decoding. eNeuro, 2020; 7(4):ENEURO.0506–ENEU19.2020.

13.

Graves

, Graves

. (2012). “Long short-term memory”. In: Supervised Sequence Labelling with Recurrent Neural Networks , Springer, pp. 37–45.

14.

Horowitz

. (2014). “1.1 Computing’s energy problem (and what we can do about it)”. In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC). . IEEE, pp. 10–14; doi: 10.1109/ISSCC.2014.6757323

15.

Kaczmarek

. The portable Neuromodulation Stimulator (PoNS) for neurorehabilitation. Scientia Iranica, 2017; 24:3171–3180.

16.

Laurence-Chasen

, Ross

, Arce-McShane

, et al. Robust cortical encoding of 3D tongue shape during feeding in macaques. Nat Commun, 2023; 14(1):2991.

17.

Lee

, Lee

, Lin

, et al. (2019). “Real-time calcium imaging based neural decoding with a support vector machine”. In: 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS) . IEEE, pp. 1–4.

18.

Lee

, Madayambath

, Liu

, et al. (2017). “Online learning in neural decoding using incremental linear discriminant analysis”. In: 2017 IEEE International Conference on Cyborg and Bionic Systems (CBS). IEEE, pp. 173–177.

19.

Livezey

, Glaser

. Deep learning approaches for neural decoding across architectures and recording modalities. Brief Bioinform, 2021; 22(2):1577–1591.

20.

Lozano

, Lipsman

, Bergman

, et al. Deep brain stimulation: Current challenges and future directions. Nat Rev Neurol, 2019; 15(3):148–160.

21.

Luu

, Nakagome

, He

, et al. Real-time EEG-based brain-computer interface to a virtual avatar enhances cortical involvement in human treadmill walking. Sci Rep, 2017; 7(1):8895.

22.

Naufel

, Glaser

, Kording

, et al. A muscle-activity-dependent gain between motor cortex and EMG. J Neurophysiol, 2019; 121(1):61–73.

23.

Ouyang

, Lu

, Zhang

, et al. A wireless and battery-less implant for multimodal closed-loop neuromodulation in small animals. Nat Biomed Eng, 2023; 7(10):1252–1269.

24.

Pandarinath

, O’Shea

, Collins

, et al. Inferring single-trial neural population dynamics using sequential auto-encoders. Nat Methods, 2018; 15(10):805–815.

25.

Pari

, Sandhya

, Sankar

. (2018). “A Multi-Tier Stacked Ensemble Algorithm to Reduce the Regret of Incremental Learning for Streaming Data”. IEEE Access. 6, pp. 48726–48739.

26.

Ramot

, Martin

. Closed-loop neuromodulation for studying spontaneous activity and causality. Trends Cogn Sci, 2022; 26(4):290–299.

27.

Saeidi

, Karwowski

, Farahani

, et al. Neural decoding of EEG signals with machine learning: A systematic review. Brain Sci, 2021; 11(11):1525.

28.

Sani

, Pesaran

, Shanechi

. Dissociative and prioritized modeling of behaviorally relevant neural dynamics using recurrent neural networks. Nat Neurosci, 2024; 27(10):2033–2045.

29.

Scangos

, Khambhati

, Daly

, et al. Closed-loop neuromodulation in an individual with treatment-resistant depression. Nat Med, 2021; 27(10):1696–1700.

30.

Schuster

, K

. Bidirectional recurrent neural networks. IEEE Trans Signal Process, 1997; 45(11):2673–2681.

31.

Shaikh

, So

, Sibindi

, et al. (2019). “Real-time closed loop neural decoding on a neuromorphic chip”. In: 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER). . IEEE, pp. 670–673.

32.

Shanechi

, Orsborn

, Carmena

. Robust brain-machine interface design using optimal feedback control modeling and adaptive point process filtering. PLoS Comput Biol, 2016; 12(4):e1004730.

33.

Stanslaski

, Afshar

, Cong

, et al. Design and validation of a fully implantable, chronic, closed-loop neuromodulation device with concurrent sensing and stimulation. IEEE Trans Neural Syst Rehabil Eng, 2012; 20(4):410–421.

34.

Sze

, Chen

Y-H

, Yang

T-J

, et al. Efficient processing of deep neural networks: A tutorial and survey. Proc IEEE, 2017; 105(12):2295–2329; doi: 10.1109/JPROC.2017.2761740

35.

Taeckens

, Dong

, Shah

. (2023). “A Biologically Plausible Spiking Neural Network for Decoding Kinematics in the Hippocampus and Premotor Cortex”. In: 2023 11th International IEEE/EMBS Conference on Neural Engineering (NER) . IEEE, pp. 1–4.

36.

Tang

, Lin

, Li

. Using domain adaptation for incremental SVM classification of drift data. Mathematics, 2022; 10(19):3579.

37.

Tseng

P-H

, Urpi

, Lebedev

, et al. Decoding movements from cortical ensemble activity using a long short-term memory recurrent network. Neural Comput, 2019; 31(6):1085–1113.

38.

Wang

, Zhou

, Li

, et al. Neural decoding of Chinese sign language with machine learning for brain–computer interfaces. IEEE Trans Neural Syst Rehabil Eng, 2021; 29:2721–2732.

39.

Xie

, Schwartz

, Prasad

. Decoding of finger trajectory from ECoG using deep learning. J Neural Eng, 2018; 15(3):36009.