no code implementations • 30 Apr 2024 • Guobin Shen, Dongcheng Zhao, Xiang He, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng
This extractor consolidates multi-level visual features into one network, simplifying integration with Large Language Models (LLMs).
no code implementations • 29 Feb 2024 • Yi Zeng, Feifei Zhao, Yuxuan Zhao, Dongcheng Zhao, Enmeng Lu, Qian Zhang, Yuwei Wang, Hui Feng, Zhuoya Zhao, Jihang Wang, Qingqun Kong, Yinqian Sun, Yang Li, Guobin Shen, Bing Han, Yiting Dong, Wenxuan Pan, Xiang He, Aorigele Bao, Jin Wang
In this paper, we introduce a Brain-inspired and Self-based Artificial Intelligence (BriSe AI) paradigm.
2 code implementations • 22 Jan 2024 • Sicheng Shen, Dongcheng Zhao, Guobin Shen, Yi Zeng
Spiking Neural Networks (SNNs), as the third generation of neural networks, have gained prominence for their biological plausibility and computational efficiency, especially in processing diverse datasets.
no code implementations • 12 Dec 2023 • Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Jindong Li, Kang Sun, Yi Zeng
Within the complex neuroarchitecture of the brain, astrocytes play crucial roles in development, structure, and metabolism.
no code implementations • 17 Nov 2023 • Guobin Shen, Dongcheng Zhao, Tenglong Li, Jindong Li, Yi Zeng
This paper introduces a unified perspective, illustrating that the time steps in SNNs and quantized bit-widths of activation values present analogous representations.
no code implementations • 28 Sep 2023 • Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng
As a further step in supporting high-performance SNNs on specialized hardware, we introduce FireFly v2, an FPGA SNN accelerator that can address the issue of non-spike operation in current SOTA SNN algorithms, which presents an obstacle in the end-to-end deployment onto existing SNN hardware.
no code implementations • 23 Aug 2023 • Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Feifei Zhao, Yi Zeng
This shift in focus from weight adjustment to mastering the intricacies of synaptic change offers a more flexible and dynamic pathway for neural networks to evolve and adapt.
1 code implementation • 9 Aug 2023 • Bing Han, Feifei Zhao, Yi Zeng, Wenxuan Pan, Guobin Shen
In addition, the overlapping shared structure helps to quickly leverage all acquired knowledge to new tasks, empowering a single network capable of supporting multiple incremental tasks (without the separate sub-network mask for each task).
no code implementations • 23 May 2023 • Dongcheng Zhao, Guobin Shen, Yiting Dong, Yang Li, Yi Zeng
Notably, our algorithm has achieved state-of-the-art performance on neuromorphic datasets DVS-CIFAR10 and N-Caltech101, and can achieve superior performance in the test phase with timestep T=1.
no code implementations • 19 May 2023 • Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Yi Zeng
The biological neural network is a vast and diverse structure with high neural heterogeneity.
no code implementations • 21 Apr 2023 • Wenxuan Pan, Feifei Zhao, Guobin Shen, Yi Zeng
The neural motifs topology, modular regional structure and global cross-brain region connection of the human brain are the product of natural evolution and can serve as a perfect reference for designing brain-inspired SNN architecture.
1 code implementation • 23 Mar 2023 • Xiang He, Dongcheng Zhao, Yang Li, Guobin Shen, Qingqun Kong, Yi Zeng
In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data.
no code implementations • 29 Jan 2023 • Guobin Shen, Dongcheng Zhao, Yi Zeng
Inspired by spike patterns in biological neurons, this paper introduces the dynamic Burst pattern and designs the Leaky Integrate and Fire or Burst (LIFB) neuron that can make a trade-off between short-time performance and dynamic temporal performance from the perspective of network information capacity.
no code implementations • 5 Jan 2023 • Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng
To improve memory efficiency, we design a memory system to enable efficient synaptic weights and membrane voltage memory access with reasonable on-chip RAM consumption.
no code implementations • 23 Nov 2022 • Bing Han, Feifei Zhao, Yi Zeng, Guobin Shen
The proposed DPAP model considers multiple biologically realistic mechanisms (such as dendritic spine dynamic plasticity, activity-dependent neural spiking trace, and local synaptic plasticity), with the addition of an adaptive pruning strategy, so that the network structure can be dynamically optimized during learning without any pre-training and retraining.
no code implementations • 18 Jul 2022 • Yi Zeng, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yiting Dong, Enmeng Lu, Qian Zhang, Yinqian Sun, Qian Liang, Yuxuan Zhao, Zhuoya Zhao, Hongjian Fang, Yuwei Wang, Yang Li, Xin Liu, Chengcheng Du, Qingqun Kong, Zizhe Ruan, Weida Bi
These brain-inspired AI models have been effectively validated on various supervised, unsupervised, and reinforcement learning tasks, and they can be used to enable AI models to be with multiple brain-inspired cognitive functions.
no code implementations • 24 May 2022 • Guobin Shen, Dongcheng Zhao, Yi Zeng
Data augmentation can improve the quantity and quality of the original data by processing more representations from the original data.
no code implementations • 24 May 2022 • Jihang Wang, Dongcheng Zhao, Guobin Shen, Qian Zhang, Yi Zeng
Privacy protection is a crucial issue in machine learning algorithms, and the current privacy protection is combined with traditional artificial neural networks based on real values.
no code implementations • 17 Oct 2021 • Guobin Shen, Dongcheng Zhao, Yi Zeng
Secondly, we propose a biologically plausible temporal adjustment making the error propagate across the spikes in the temporal dimension, which overcomes the problem of the temporal dependency within a single spike period of the traditional spiking neurons.