Generative models based on neural networks present a substantial challenge within deep learning. As it stands, such models are primarily limited to the domain of artificial neural networks. Spiking neural networks, as the third generation of neural networks, offer a closer approximation to brain-like processing due to their rich spatiotemporal dynamics. However, generative models based on spiking neural networks are not well studied. In this work, we pioneer constructing a spiking generative adversarial network capable of handling complex images. Our first task was to identify the problems of out-of-domain inconsistency and temporal inconsistency inherent in spiking generative adversarial networks. We addressed these issues by incorporating the Earth-Mover distance and an attention-based weighted decoding method, significantly enhancing the performance of our algorithm across several datasets. Experimental results reveal that our approach outperforms existing methods on the MNIST, FashionMNIST, CIFAR10, and CelebA datasets. Moreover, compared with hybrid spiking generative adversarial networks, where the discriminator is an artificial analog neural network, our methodology demonstrates closer alignment with the information processing patterns observed in the mouse.

翻译：基于神经网络的生成模型是深度学习中的重大挑战。当前，这类模型主要局限于人工神经网络领域。作为第三代神经网络，脉冲神经网络因其丰富的时空动态特性，能够更接近类脑信息处理过程。然而，基于脉冲神经网络的生成模型尚未得到充分研究。本文率先构建了能够处理复杂图像的脉冲生成对抗网络。我们首先识别出脉冲生成对抗网络中固有的域外不一致性与时间一致性问题。通过引入推土机距离与基于注意力的加权解码方法，我们显著提升了算法在多个数据集上的性能。实验结果表明，我们的方法在MNIST、FashionMNIST、CIFAR10和CelebA数据集上均优于现有方法。此外，与判别器采用人工模拟神经网络的混合脉冲生成对抗网络相比，我们的方法更贴近小鼠信息处理模式。