Direct learning-based deep spiking neural networks: a review

Guo, Yufei; Huang, Xuhui; Ma, Zhe

doi:10.3389/fnins.2023.1209795

Cited by 18 publications

(3 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SNNs, inspired by biological neurons, excel in energy efficiency and event-driven computation, making them ideal for neuromorphic computing and real-time applications. SNNs offer promising applications due to their resemblance to biological brains and unique computational capabilities [ 157 ]. Particularly in neuromorphic engineering, SNNs closely mimic biological brain functions, making them ideal for tasks like sensory processing, pattern recognition, and motor control in robots and autonomous systems [ 158 , 159 ].…”

Section: Discussion On Pnns and Concluding Remarksmentioning

confidence: 99%

Exploring Types of Photonic Neural Networks for Imaging and Computing—A Review

Khonina,

Kazanskiy,

Skidanov

et al. 2024

Nanomaterials

View full text Add to dashboard Cite

Photonic neural networks (PNNs), utilizing light-based technologies, show immense potential in artificial intelligence (AI) and computing. Compared to traditional electronic neural networks, they offer faster processing speeds, lower energy usage, and improved parallelism. Leveraging light’s properties for information processing could revolutionize diverse applications, including complex calculations and advanced machine learning (ML). Furthermore, these networks could address scalability and efficiency challenges in large-scale AI systems, potentially reshaping the future of computing and AI research. In this comprehensive review, we provide current, cutting-edge insights into diverse types of PNNs crafted for both imaging and computing purposes. Additionally, we delve into the intricate challenges they encounter during implementation, while also illuminating the promising perspectives they introduce to the field.

show abstract

Section: Discussion On Pnns and Concluding Remarksmentioning

confidence: 99%

Exploring Types of Photonic Neural Networks for Imaging and Computing—A Review

Khonina,

Kazanskiy,

Skidanov

et al. 2024

Nanomaterials

View full text Add to dashboard Cite

show abstract

“…Such methods (Wu et al, 2018 ; Neftci et al, 2019 ; Lee et al, 2020 ) usually obtain low latency and can train SNNs with small simulation time steps. Recently, in addition to designing powerful spiking neurons (Fang et al, 2021b ; Li et al, 2022 ; Yao et al, 2022 ), researchers have primarily improved the accuracy of direct-training SNNs from network structure and training techniques (Guo et al, 2023 ). We will elaborate on them.…”

Section: Related Workmentioning

confidence: 99%

Direct training high-performance spiking neural networks for object recognition and detection

Zhang

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionThe spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous crucial issues to explore for the deployment of direct training SNNs, such as gradient vanishing and explosion, spiking signal decoding, and applications in upstream tasks.MethodsTo address gradient vanishing, we introduce a binary selection gate into the basic residual block and propose spiking gate (SG) ResNet to implement residual learning in SNNs. We propose two appropriate representations of the gate signal and verify that SG ResNet can overcome gradient vanishing or explosion by analyzing the gradient backpropagation. For the spiking signal decoding, a better decoding scheme than rate coding is achieved by our attention spike decoder (ASD), which dynamically assigns weights to spiking signals along the temporal, channel, and spatial dimensions.Results and discussionThe SG ResNet and ASD modules are evaluated on multiple object recognition datasets, including the static ImageNet, CIFAR-100, CIFAR-10, and neuromorphic DVS-CIFAR10 datasets. Superior accuracy is demonstrated with a tiny simulation time step of four, specifically 94.52% top-1 accuracy on CIFAR-10 and 75.64% top-1 accuracy on CIFAR-100. Spiking RetinaNet is proposed using SG ResNet as the backbone and ASD module for information decoding as the first direct-training hybrid SNN-ANN detector for RGB images. Spiking RetinaNet with a SG ResNet34 backbone achieves an mAP of 0.296 on the object detection dataset MSCOCO.

show abstract

“…In order to facilitate effective training of SNNs, researchers have proposed various methods [ 7 , 8 , 9 ]. Present research predominantly concentrates on three major aspects: pretraining through clustering and autoencoding, among other methods, under unsupervised learning; enhancing performance by combining supervised information and unlabeled data under semisupervised learning; and implementing backpropagation under supervised learning using alternative differentiable activation functions or other techniques.…”

Section: Introductionmentioning

confidence: 99%

Learnable Leakage and Onset-Spiking Self-Attention in SNNs with Local Error Signals

Shi,

Wang,

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

Spiking neural networks (SNNs) have garnered significant attention due to their computational patterns resembling biological neural networks. However, when it comes to deep SNNs, how to focus on critical information effectively and achieve a balanced feature transformation both temporally and spatially becomes a critical challenge. To address these challenges, our research is centered around two aspects: structure and strategy. Structurally, we optimize the leaky integrate-and-fire (LIF) neuron to enable the leakage coefficient to be learnable, thus making it better suited for contemporary applications. Furthermore, the self-attention mechanism is introduced at the initial time step to ensure improved focus and processing. Strategically, we propose a new normalization method anchored on the learnable leakage coefficient (LLC) and introduce a local loss signal strategy to enhance the SNN’s training efficiency and adaptability. The effectiveness and performance of our proposed methods are validated on the MNIST, FashionMNIST, and CIFAR-10 datasets. Experimental results show that our model presents a superior, high-accuracy performance in just eight time steps. In summary, our research provides fresh insights into the structure and strategy of SNNs, paving the way for their efficient and robust application in practical scenarios.

show abstract

Direct learning-based deep spiking neural networks: a review

Cited by 18 publications

References 104 publications

Exploring Types of Photonic Neural Networks for Imaging and Computing—A Review

Exploring Types of Photonic Neural Networks for Imaging and Computing—A Review

Direct training high-performance spiking neural networks for object recognition and detection

Learnable Leakage and Onset-Spiking Self-Attention in SNNs with Local Error Signals

Contact Info

Product

Resources

About