Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Linghao, Zhao, Dongcheng, Shen, Sicheng, Dong, Yiting, Shen, Guobin, Zeng, Yi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916257641529344
author Feng, Linghao
Zhao, Dongcheng
Shen, Sicheng
Dong, Yiting
Shen, Guobin
Zeng, Yi
author_facet Feng, Linghao
Zhao, Dongcheng
Shen, Sicheng
Dong, Yiting
Shen, Guobin
Zeng, Yi
contents This paper presents a novel approach leveraging Spiking Neural Networks (SNNs) to construct a Variational Quantized Autoencoder (VQ-VAE) with a temporal codebook inspired by hippocampal time cells. This design captures and utilizes temporal dependencies, significantly enhancing the generative capabilities of SNNs. Neuroscientific research has identified hippocampal "time cells" that fire sequentially during temporally structured experiences. Our temporal codebook emulates this behavior by triggering the activation of time cell populations based on similarity measures as input stimuli pass through it. We conducted extensive experiments on standard benchmark datasets, including MNIST, FashionMNIST, CIFAR10, CelebA, and downsampled LSUN Bedroom, to validate our model's performance. Furthermore, we evaluated the effectiveness of the temporal codebook on neuromorphic datasets NMNIST and DVS-CIFAR10, and demonstrated the model's capability with high-resolution datasets such as CelebA-HQ, LSUN Bedroom, and LSUN Church. The experimental results indicate that our method consistently outperforms existing SNN-based generative models across multiple datasets, achieving state-of-the-art performance. Notably, our approach excels in generating high-resolution and temporally consistent data, underscoring the crucial role of temporal information in SNN-based generative modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14474
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation
Feng, Linghao
Zhao, Dongcheng
Shen, Sicheng
Dong, Yiting
Shen, Guobin
Zeng, Yi
Neural and Evolutionary Computing
This paper presents a novel approach leveraging Spiking Neural Networks (SNNs) to construct a Variational Quantized Autoencoder (VQ-VAE) with a temporal codebook inspired by hippocampal time cells. This design captures and utilizes temporal dependencies, significantly enhancing the generative capabilities of SNNs. Neuroscientific research has identified hippocampal "time cells" that fire sequentially during temporally structured experiences. Our temporal codebook emulates this behavior by triggering the activation of time cell populations based on similarity measures as input stimuli pass through it. We conducted extensive experiments on standard benchmark datasets, including MNIST, FashionMNIST, CIFAR10, CelebA, and downsampled LSUN Bedroom, to validate our model's performance. Furthermore, we evaluated the effectiveness of the temporal codebook on neuromorphic datasets NMNIST and DVS-CIFAR10, and demonstrated the model's capability with high-resolution datasets such as CelebA-HQ, LSUN Bedroom, and LSUN Church. The experimental results indicate that our method consistently outperforms existing SNN-based generative models across multiple datasets, achieving state-of-the-art performance. Notably, our approach excels in generating high-resolution and temporally consistent data, underscoring the crucial role of temporal information in SNN-based generative modeling.
title Time Cell Inspired Temporal Codebook in Spiking Neural Networks for Enhanced Image Generation
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2405.14474