Recent advances and new frontiers in spiking neural networks

D Zhang, S Jia, Q Wang - arxiv preprint arxiv:2204.07050, 2022‏ - arxiv.org
In recent years, spiking neural networks (SNNs) have received extensive attention in brain-
inspired intelligence due to their rich spatially-temporal dynamics, various encoding …

Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks

T Zhang, X Cheng, S Jia, M Poo, Y Zeng, B Xu - Science advances, 2021‏ - science.org
Many synaptic plasticity rules found in natural circuits have not been incorporated into
artificial neural networks (ANNs). We showed that incorporating a nonlocal feature of …

[HTML][HTML] Braincog: A spiking neural network based, brain-inspired cognitive intelligence engine for brain-inspired ai and brain simulation

Y Zeng, D Zhao, F Zhao, G Shen, Y Dong, E Lu… - Patterns, 2023‏ - cell.com
Spiking neural networks (SNNs) serve as a promising computational framework for
integrating insights from the brain into artificial intelligence (AI). Existing software …

GLSNN: A multi-layer spiking neural network based on global feedback alignment and local STDP plasticity

D Zhao, Y Zeng, T Zhang, M Shi, F Zhao - Frontiers in Computational …, 2020‏ - frontiersin.org
Spiking Neural Networks (SNNs) are considered as the third generation of artificial neural
networks, which are more closely with information processing in biological brains. However …

Research advances and new paradigms for biology-inspired spiking neural networks

T Zheng, L Han, T Zhang - arxiv preprint arxiv:2408.13996, 2024‏ - arxiv.org
Spiking neural networks (SNNs) are gaining popularity in the computational simulation and
artificial intelligence fields owing to their biological plausibility and computational efficiency …

Tuning convolutional spiking neural network with biologically plausible reward propagation

T Zhang, S Jia, X Cheng, B Xu - IEEE Transactions on Neural …, 2021‏ - ieeexplore.ieee.org
Spiking neural networks (SNNs) contain more biologically realistic structures and
biologically inspired learning principles than those in standard artificial neural networks …

Increasing liquid state machine performance with edge-of-chaos dynamics organized by astrocyte-modulated plasticity

V Ivanov, K Michmizos - Advances in neural information …, 2021‏ - proceedings.neurips.cc
The liquid state machine (LSM) combines low training complexity and biological plausibility,
which has made it an attractive machine learning framework for edge and neuromorphic …

[HTML][HTML] Backeisnn: A deep spiking neural network with adaptive self-feedback and balanced excitatory–inhibitory neurons

D Zhao, Y Zeng, Y Li - Neural Networks, 2022‏ - Elsevier
Spiking neural networks (SNNs) transmit information through discrete spikes that perform
well in processing spatial–temporal information. Owing to their nondifferentiable …

Meta neurons improve spiking neural networks for efficient spatio-temporal learning

X Cheng, T Zhang, S Jia, B Xu - Neurocomputing, 2023‏ - Elsevier
Spiking neural networks (SNNs) have incorporated many biologically-plausible structures
and learning principles, and hence are playing critical roles in bridging the gap between …

Spike calibration: Fast and accurate conversion of spiking neural network for object detection and segmentation

Y Li, X He, Y Dong, Q Kong, Y Zeng - arxiv preprint arxiv:2207.02702, 2022‏ - arxiv.org
Spiking neural network (SNN) has been attached to great importance due to the properties
of high biological plausibility and low energy consumption on neuromorphic hardware. As …