PrivateSNN: Privacy-Preserving Spiking Neural Networks

Kim, Youngeun; Venkatesha, Yeshwanth; Panda, Priyadarshini

doi:10.48550/arxiv.2104.03414

Cited by 4 publications

(4 citation statements)

References 35 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case where the source training data is private or unavailable due to copyright issues, we can generate fake data by inverting the knowledge learned in the pre-trained ANN [81]. Doing so can remove the reliance on collecting calibration data from the training dataset.…”

Section: Calibration Without Training Datamentioning

confidence: 99%

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

Li¹,

Deng²,

Dong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Spiking Neural Network (SNN), originating from the neural behavior in biology, has been recognized as one of the nextgeneration neural networks. Conventionally, SNNs can be obtained by converting from pre-trained Artificial Neural Networks (ANNs) by replacing the non-linear activation with spiking neurons without changing the parameters. In this work, we argue that simply copying and pasting the weights of ANN to SNN inevitably results in activation mismatch, especially for ANNs that are trained with batch normalization (BN) layers. To tackle the activation mismatch issue, we first provide a theoretical analysis by decomposing local conversion error to clipping error and flooring error, and then quantitatively measure how this error propagates throughout the layers using the second-order analysis. Motivated by the theoretical results, we propose a set of layer-wise parameter calibration algorithms, which adjusts the parameters to minimize the activation mismatch. Extensive experiments for the proposed algorithms are performed on modern architectures and large-scale tasks including ImageNet classification and MS COCO detection. We demonstrate that our method can handle the SNN conversion with batch normalization layers and effectively preserve the high accuracy even in 32 time steps. For example, our calibration algorithms can increase up to 65% accuracy when converting VGG-16 with BN layers.

show abstract

Section: Calibration Without Training Datamentioning

confidence: 99%

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

Li¹,

Deng²,

Dong³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Spiking neural networks (SNNs) have emerged as the next generation of neural networks [5,[28][29][30][31][32][33][34], because they offer huge energy-efficiency advantage over ANNs. Different from standard ANNs that make use of float values, SNNs process binary spikes (0 or 1) across multiple time-steps.…”

Section: Spiking Neural Networkmentioning

confidence: 99%

Beyond classification: directly training spiking neural networks for semantic segmentation

Kim

Chough

Panda

2022

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) have recently emerged as the low-power alternative to Artificial Neural Networks (ANNs) because of their sparse, asynchronous, and binary event-driven processing. Due to their energy efficiency, SNNs have a high possibility of being deployed for real-world, resource-constrained systems such as autonomous vehicles and drones. However, owing to their non-differentiable and complex neuronal dynamics, most previous SNN optimization methods have been limited to image recognition. In this paper, we explore the SNN applications beyond classification and present semantic segmentation networks configured with spiking neurons. Specifically, we first investigate two representative SNN optimization techniques for recognition tasks (i.e., ANN-SNN conversion and surrogate gradient learning) on semantic segmentation datasets. We observe that, when converted from ANNs, SNNs suffer from high latency and low performance due to the spatial variance of features. Therefore, we directly train networks with surrogate gradient learning, resulting in lower latency and higher performance than ANN-SNN conversion. Moreover, we redesign two fundamental ANN segmentation architectures (i.e., Fully Convolutional Networks and DeepLab) for the SNN domain. We conduct experiments on two public semantic segmentation benchmarks including the PASCAL VOC2012 dataset and the DDD17 event-based dataset. In addition to showing the feasibility of SNNs for semantic segmentation, we show that SNNs can be more robust and energy-efficient compared to their ANN counterparts in this domain.

show abstract

“…Spiking Neural Networks (SNNs) have emerged as the next generation of neural networks [5], [28], [29], [30], [31], [32], [33], [34], because they offer huge energy-efficiency advantage over ANNs. Different from standard ANNs that make use of float values, SNNs process binary spikes (0 or 1) across multiple time-steps.…”

Section: Related Work a Spiking Neural Networkmentioning

confidence: 99%

Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation

Kim¹,

Chough²,

Panda³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) have recently emerged as the low-power alternative to Artificial Neural Networks (ANNs) because of their sparse, asynchronous, and binary event-driven processing. Due to their energy efficiency, SNNs have a high possibility of being deployed for real-world, resourceconstrained systems such as autonomous vehicles and drones. However, owing to their non-differentiable and complex neuronal dynamics, most previous SNN optimization methods have been limited to image recognition. In this paper, we explore the SNN applications beyond classification and present semantic segmentation networks configured with spiking neurons. Specifically, we first investigate two representative SNN optimization techniques for recognition tasks (i.e., ANN-SNN conversion and surrogate gradient learning) on semantic segmentation datasets. We observe that, when converted from ANNs, SNNs suffer from high latency and low performance due to the spatial variance of features. Therefore, we directly train networks with surrogate gradient learning, resulting in lower latency and higher performance than ANN-SNN conversion. Moreover, we redesign two fundamental ANN segmentation architectures (i.e., Fully Convolutional Networks and DeepLab) for the SNN domain. We conduct experiments on two public semantic segmentation benchmarks including the PASCAL VOC2012 dataset and the DDD17 event-based dataset. In addition to showing the feasibility of SNNs for semantic segmentation, we show that SNNs can be more robust and energy-efficient compared to their ANN counterparts in this domain.

show abstract

PrivateSNN: Privacy-Preserving Spiking Neural Networks

Cited by 4 publications

References 35 publications

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

Beyond classification: directly training spiking neural networks for semantic segmentation

Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation

Contact Info

Product

Resources

About