DCT-SNN: Using DCT to Distribute Spatial Information over Time for Low-Latency Spiking Neural Networks

Garg, Isha; Chowdhury, Sayeed Shafayet; Roy, Kaushik

doi:10.1109/iccv48922.2021.00463

Cited by 23 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, some of the recent SCNN implementations favor more straightforward Pooling options. AveragePool (Wu et al, 2018 ; Sengupta et al, 2019 ; Garg et al, 2021 ; Yan et al, 2021 ) and Strided Convolutional layers (Esser et al, 2016 ; Patel et al, 2021 ) are some of the straightforward alternatives to the spiking MaxPooling. However, even in the spike domain, the MaxPooling tends to produce higher classification accuracy (Rueckauer et al, 2017 ) than the aforementioned alternatives.…”

Section: Sub-sampling By Pooling Operationmentioning

confidence: 99%

Spiking CMOS-NVM mixed-signal neuromorphic ConvNet with circuit- and training-optimized temporal subsampling

Dorzhigulov

Saxena

2023

Front. Neurosci.

View full text Add to dashboard Cite

We increasingly rely on deep learning algorithms to process colossal amount of unstructured visual data. Commonly, these deep learning algorithms are deployed as software models on digital hardware, predominantly in data centers. Intrinsic high energy consumption of Cloud-based deployment of deep neural networks (DNNs) inspired researchers to look for alternatives, resulting in a high interest in Spiking Neural Networks (SNNs) and dedicated mixed-signal neuromorphic hardware. As a result, there is an emerging challenge to transfer DNN architecture functionality to energy-efficient spiking non-volatile memory (NVM)-based hardware with minimal loss in the accuracy of visual data processing. Convolutional Neural Network (CNN) is the staple choice of DNN for visual data processing. However, the lack of analog-friendly spiking implementations and alternatives for some core CNN functions, such as MaxPool, hinders the conversion of CNNs into the spike domain, thus hampering neuromorphic hardware development. To address this gap, in this work, we propose MaxPool with temporal multiplexing for Spiking CNNs (SCNNs), which is amenable for implementation in mixed-signal circuits. In this work, we leverage the temporal dynamics of internal membrane potential of Integrate & Fire neurons to enable MaxPool decision-making in the spiking domain. The proposed MaxPool models are implemented and tested within the SCNN architecture using a modified version of the aihwkit framework, a PyTorch-based toolkit for modeling and simulating hardware-based neural networks. The proposed spiking MaxPool scheme can decide even before the complete spatiotemporal input is applied, thus selectively trading off latency with accuracy. It is observed that by allocating just 10% of the spatiotemporal input window for a pooling decision, the proposed spiking MaxPool achieves up to 61.74% accuracy with a 2-bit weight resolution in the CIFAR10 dataset classification task after training with back propagation, with only about 1% performance drop compared to 62.78% accuracy of the 100% spatiotemporal window case with the 2-bit weight resolution to reflect foundry-integrated ReRAM limitations. In addition, we propose the realization of one of the proposed spiking MaxPool techniques in an NVM crossbar array along with periphery circuits designed in a 130nm CMOS technology. The energy-efficiency estimation results show competitive performance compared to recent neuromorphic chip designs.

show abstract

Section: Sub-sampling By Pooling Operationmentioning

confidence: 99%

Spiking CMOS-NVM mixed-signal neuromorphic ConvNet with circuit- and training-optimized temporal subsampling

Dorzhigulov

Saxena

2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Similar strategies have been popular since the 1980s (see e.g., [13,14]) for their simplicity and overall good performances. In the deep learning era, VQ-like approaches were rediscovered [12], as was the case with other compression techniques [15,16].…”

Section: Latent-space Encodingmentioning

confidence: 99%

Denoising Diffusion Models on Model-Based Latent Space

Scribano,

Pezzi,

Franchini

et al. 2023

Algorithms

View full text Add to dashboard Cite

With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by abstracting away imperceptible image details and introducing substantial spatial compression, renders the learning of the generative process more manageable while significantly reducing computational and memory demands. In this work, we propose to replace autoencoder coding with a model-based coding scheme based on traditional lossy image compression techniques; this choice not only further diminishes computational expenses but also allows us to probe the boundaries of latent-space image generation. Our objectives culminate in the proposal of a valuable approximation for training continuous diffusion models within a discrete space, accompanied by enhancements to the generative model for categorical values. Beyond the good results obtained for the problem at hand, we believe that the proposed work holds promise for enhancing the adaptability of generative diffusion models across diverse data types beyond the realm of imagery.

show abstract

“…In principle, SNNs can be used for the same applications as ANNs. Despite the potential advantages with respect to energy efficiency, because of the lower scalability of SNNs models, the research in the SNNs field has been typically focused on datasets, such as MNIST [8][9][10][11], N-MNIST [12][13][14][15][16], Fashion-MNIST [17][18][19][20], and CIFAR10 [21][22][23][24][25]. Therefore, this paper examines the applicability of SNNs to real-world applications, such as scene classification problems (satellite dataset) and forecasting epileptic seizure in the healthcare field.…”

Section: Energy Gapmentioning

confidence: 99%

A Deep Convolutional Spiking Neural Network for Embedded Applications

Javanshir,

Nguyen,

Mahmud

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

DCT-SNN: Using DCT to Distribute Spatial Information over Time for Low-Latency Spiking Neural Networks

Cited by 23 publications

References 34 publications

Spiking CMOS-NVM mixed-signal neuromorphic ConvNet with circuit- and training-optimized temporal subsampling

Spiking CMOS-NVM mixed-signal neuromorphic ConvNet with circuit- and training-optimized temporal subsampling

Denoising Diffusion Models on Model-Based Latent Space

A Deep Convolutional Spiking Neural Network for Embedded Applications

Contact Info

Product

Resources

About