BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation

@article{Zeng2022BrainCogAS,
  title={BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation},
  author={Yi Zeng and Dongcheng Zhao and Feifei Zhao and Guobin Shen and Yiting Dong and Enmeng Lu and Qian Zhang and Yinqian Sun and Qian Liang and Yuxuan Zhao and Zhuoya Zhao and Hongjian Fang and Yuwei Wang and Yang Li and Xin Liu and Chen-Yu Du and Qingqun Kong and Zizhe Ruan and Weida Bi},
  journal={ArXiv},
  year={2022},
  volume={abs/2207.08533}
}
—Spiking neural networks (SNNs) have attracted extensive attentions in Brain-inspired Artificial Intelligence and computational neuroscience. They can be used to simulate biological information processing in the brain from multiple scales, including membrane potential, neuronal firing, synap- tic transmission, synaptic plasticity, and multiple brain areas coordination. More importantly, SNNs serve as an appropriate level of abstraction to bring inspirations from brain and cognition to Artificial… 

Adaptive Sparse Structure Development with Pruning and Regeneration for Spiking Neural Networks

This paper proposed a novel method for the adaptive structural development of SNN (SD-SNN), introducing dendritic spine plasticity-based synaptic constraint, neuronal pruning and synaptic regeneration, and found that synaptic constraint and neuronal pruned can detect and remove a large amount of redundancy in SNNs, coupled with synaptic regeneration can effectively prevent and repair over-pruning.

References

SHOWING 1-10 OF 171 REFERENCES

Brain-inspired Graph Spiking Neural Networks for Commonsense Knowledge Representation and Reasoning

This work investigates how population encoding and spiking timing-dependent plasticity mechanisms can be integrated into the learning of spiking neural networks, and how a population of neurons can represent a symbol via guiding the completion of sequential firing between different neuron populations.

Improving multi-layer spiking neural networks by incorporating brain-inspired rules

This paper introduces seven brain-inspired rules that are deeply rooted in the understanding of the brain to improve multi-layer spiking neural networks (SNNs) and shows that higher accuracy will be achieved when more brain- inspired rules are integrated into the learning procedure.

Parallel Brain Simulator: A Multi-scale and Parallel Brain-Inspired Neural Network Modeling and Simulation Platform

This paper presents the parallel brain simulator (PBS), a parallel and distributed platform for modeling the cognitive brain at multiple scales, aimed at reducing the complexity of distributed programming and providing an easy to use programmable platform for computational neuroscientists and artificial intelligence researchers for modeling and simulation of large-scale neural networks.

Brain-inspired Balanced Tuning for Spiking Neural Networks

The proposed approach is verified on the MNIST hand-written digit recognition dataset and the performance indicates that the ideas of balancing state could indeed improve the learning ability of SNNs, which shows the power of proposed brain-inspired approach on the tuning of biological plausible SNN's.

A Spiking Neural Network Based Autonomous Reinforcement Learning Model and Its Application in Decision Making

The proposed model is an expansion of the basal ganglia circuitry with automatic environment perception that automatically constructs environmental states from image inputs and can automatically generate rules to play well in the “flappy bird” game.

Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory

A spiking neural network based on psychological and neurobiological findings at multiple scales that can store a huge amount of data on melodies and recall them with high accuracy and can remember the entirety of a melody given only an episode or the melody played at different paces.

A Brain-Inspired Causal Reasoning Model Based on Spiking Neural Networks

  • H. FangYi Zeng
  • Computer Science
    2021 International Joint Conference on Neural Networks (IJCNN)
  • 2021
Inspired by the human brain, Causal Reasoning Spiking Neural Network (CRSNN) is proposed to implement the causal reasoning with STDP learning rule and population coding mechanism and is used for the first time that SNN is used to complete causal reasoning tasks.

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

It is argued that this package facilitates the use of spiking networks for large-scale machine learning problems and some simple examples by using BindsNET in practice are shown.

An Unsupervised Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections

An adaptive synaptic plasticity is designed, and the adaptive threshold balance is introduced as the neuron plasticity to enrich the representation ability of SNNs and introduce an adaptive lateral inhibitory connection to dynamically adjust the spikes balance to help the network learn richer features.
...