论文标题
优化的尖峰神经元通过两个尖峰通过时间编码来高精度地对图像进行分类
Optimized spiking neurons classify images with high accuracy through temporal coding with two spikes
论文作者
论文摘要
基于SPIKE的神经形态硬件有望减少图像分类和其他深度学习应用程序的能源消耗，尤其是在手机或其他边缘设备上。但是，对深尖峰神经网络的直接训练很困难，并且以前将训练有素的人工神经网络转换为尖峰神经元的方法效率低下，因为神经元必须发出太多的尖峰。我们表明，当人们为此目的优化尖峰神经元模型时，就会产生更有效的转换，因此，这不仅对信息传递至关重要，而且当它发出这些尖峰时，它也会发出多少个尖峰。这可以提高使用尖峰神经元的图像分类可以达到的准确性，而所得网络平均只需要每个神经元两个尖峰才能分类图像。此外，我们的新转换方法改善了所得尖峰网络的延迟和吞吐量。
Spike-based neuromorphic hardware promises to reduce the energy consumption of image classification and other deep learning applications, particularly on mobile phones or other edge devices. However, direct training of deep spiking neural networks is difficult, and previous methods for converting trained artificial neural networks to spiking neurons were inefficient because the neurons had to emit too many spikes. We show that a substantially more efficient conversion arises when one optimizes the spiking neuron model for that purpose, so that it not only matters for information transmission how many spikes a neuron emits, but also when it emits those spikes. This advances the accuracy that can be achieved for image classification with spiking neurons, and the resulting networks need on average just two spikes per neuron for classifying an image. In addition, our new conversion method improves latency and throughput of the resulting spiking networks.
