Brain-Inspired Computing
🧠 Brain Signal Analysis
We are dedicated to deciphering multimodal brain signals to uncover fundamental neural mechanisms and develop non-invasive brain-computer interfaces (BCIs) for medical rehabilitation and human augmentation. To this end, we are collecting large-scale multimodal neural recordings (EEG, fNIRS, MEG) and developing open-source software toolkits to enable efficient, standardized analysis of complex neural data. Furthermore, we leverage these datasets to train foundation models for brain signal interpretation, which significantly enhance cross-subject generalization, cross-trial consistency, and multi-task adaptability. These advances will translate to practical applications such as brain disease analysis, neural-steered hearing aids, and neuroprosthetics, ultimately enhancing life quality for individuals with neurological disorders.
⚙️ Brain-Inspired Computing
Brain-inspired computing emulates the physical architecture and operational principles of biological neural systems to fundamentally advance the energy efficiency, adaptability, and intelligence of artificial intelligence. Our research decodes the structural hierarchy of the human brain and translates it into powerful computational models that improve the energy efficiency and capabilities of artificial neural networks (ANNs). Additionally, we explore various forms of neural plasticity in animal brains and develop advanced algorithms to enhance the training efficiency and lifelong learning capabilities of ANNs. Finally, we actively engage with academic and industry collaborators specializing in neuromorphic hardware design to create neuromorphic cognitive systems that address real-world challenges in AI agents, autonomous systems, and smart wearables.
📝 Representative Publications
A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks
J. Wu, Y. Chua, M. Zhang, G. Li, H. Li and K. C. Tan
IEEE Trans. on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 446-460, Jan. 2023 | Learning Algorithm
Progressive Tandem Learning for Pattern Recognition With Deep Spiking Neural Networks
J. Wu, C. Xu, X. Han, D. Zhou, M. Zhang, H. Li, and K. C. Tan
IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7824-7840, 1 Nov. 2022 | Learning Algorithm
A Hybrid Neural Coding Approach for Pattern Recognition With Spiking Neural Networks
X. Chen, Q. Yang, J. Wu, H. Li and K. C. Tan
IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 46, no. 5, pp. 3064-3078, May 2024 | Neural Coding
TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling
S. Zhang, Q. Yang, C. Ma, J. Wu, H. Li, and K.C. Tan
AAAI'24, March, Vancouver, Canada | Neural Architecture Design
Toward Ultralow-Power Neuromorphic Speech Enhancement With Spiking-FullSubNet
X. Hao, C. Ma, Q. Yang, J. Wu and K. C. Tan
IEEE Trans. on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2025.3566021 | Neuromorphic System, Best Paper Award in 2024 IEEE Conference on Artificial Intelligence
