Spiking Neural Networks (SNN) are the so-called third generation of neural networks which attempt to more closely match the functioning of the biological brain. They inherently encode temporal data, allowing for training with less energy usage and can be extremely energy efficient when coded on neuromorphic hardware. In addition, they are well suited for tasks involving event-based sensors, which match the event-based nature of the SNN. However, SNNs have not been as effectively applied to real-world, large-scale tasks as standard Artificial Neural Networks (ANNs) due to the algorithmic and training complexity. To exacerbate the situation further, the input representation is unconventional and requires careful analysis and deep understanding. In this paper, we propose \textit{SpikeMS}, the first deep encoder-decoder SNN architecture for the real-world large-scale problem of motion segmentation using the event-based DVS camera as input. To accomplish this, we introduce a novel spatio-temporal loss formulation that includes both spike counts and classification labels in conjunction with the use of new techniques for SNN backpropagation. In addition, we show that \textit{SpikeMS} is capable of \textit{incremental predictions}, or predictions from smaller amounts of test data than it is trained on. This is invaluable for providing outputs even with partial input data for low-latency applications and those requiring fast predictions. We evaluated \textit{SpikeMS} on challenging synthetic and real-world sequences from EV-IMO, EED and MOD datasets and achieving results on a par with a comparable ANN method, but using potentially 50 times less power.
翻译:Spik Neal Network (SNN) 是所谓的第三代神经网络, 试图更密切匹配生物大脑的功能。 它们本质上将时间数据编码为50种时间数据, 使得培训能少用能源, 在神经变异硬件编码时能够非常高的能源效率。 此外, 它们非常适合涉及事件感应器的任务, 这与 SNN 的事件性质相匹配。 但是, SNNS 并没有有效地应用于现实世界, 像标准的低度人工神经网络那样大规模的任务。 由于算法和培训的复杂性, 它们试图更接近生物大脑的功能。 为了让情况进一步恶化, 输入显示时间数据代表的是非常规的, 输入数据代表的是使用实时的电解码 S- decoder SNNN 结构, 使用基于事件的 DVS 相机作为投入。 为了达到这个目的, 我们引入了一个新型的神经神经神经网络(Orality) 数据, 显示的是SNEVS-ral-deal 时间值数据, 显示S- 和Snalal-stalal exalalalalal ex laction ex) 数据的数值值值值值数据, 实现。