top of page

Neuromorphic Computing

Since the advent of digital computers, generations of researchers are devoted to creating human-like intelligent machines that can perceive and respond to sensory stimuli, reason and plan to solve challenging problems, and create tools and art pieces. Despite we are still far from fully understanding how the brain works, learning from the brain’s information processing mechanism and system architecture represents a promising way to design more capable, efficient, robust, and explainable machines with general intelligence. The research on neuromorphic computing, therefore, occupies a major proportion in the Human Brain Project (Europe), BRAIN Initiative (USA), and China Brain Project.


The goals of our research will be to understand the neural coding, neural plasticity, and organization principles underlying biological neural systems and, ultimately, to develop low-power, robust, adaptive, and explainable neuromorphic cognitive machines. To accomplish these goals, we follow a hybrid bottom-up and top-down approach. From the bottom level, we thoroughly investigate the mechanisms and functional properties of rich and diversified neural plasticity and neural coding that originated from simple neural circuits. From the top level, we follow the taxonomy of cognitive neuroscience by developing functional modules that correspond to different brain regions and map them to low-level neural circuits according to their specific functional and operational requirements. To achieve the ultimate goal of developing neuromorphic cognitive machine, we actively engaging with academic and industry collaborators that are specialized in neuromorphic hardware design to fully realize the potential of our developed systems.

Neuromorphic Computing.png


[1] Q. Yang, J. Wu, M. Zhang, Y. Chua, X. Wang, H. Li, "Training Spiking Neural Networks with Local Tandem Learning", in Advances in Neural Information Processing Systems (2022): 14516-14528. 

[2] J. Wu, C. Xu, X. Han, D. Zhou, M. Zhang, H. Li, and K. C. Tan,"Progressive Tandem Learning for Pattern Recognition With Deep Spiking Neural Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7824-7840, 1 Nov. 2022.

[3] X. Chen, Q. Yang, J. Wu, H. Li, and K. C. Tan, "A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks", in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.

[4] Hu, J., Tang, H., Tan, K. C. and Li, H. (2016). How the brain formulates memory: A spatio-temporal model research frontier. IEEE Computational Intelligence Magazine, 11(2), 56-68. (2019 IEEE CIM Outstanding Paper Award
[5] Yu, Q., Tang, H., Tan, K. C. and Li, H. (2013). Rapid feedforward computation by temporal encoding and learning with spiking neurons. IEEE transactions on neural networks and learning systems, 24(10), 1539-1552. (2016 IEEE TNNLS Outstanding Paper Award

bottom of page