Mobile and embedded applications require neural networks-based pattern
recognition systems to perform well under a tight computational budget. In
contrast to commonly used synchronous, frame-based vision systems and CNNs,
asynchronous, spiking neural networks driven by event-based visual input
respond with low latency to sparse, salient features in the input, leading to
high efficiency at run-time. The discrete nature of the event-based data
streams makes direct training of asynchronous neural networks challenging. This
paper studies asynchronous spiking neural networks, obtained by conversion from
a conventional CNN trained on frame-based data. As an example, we consider a
CNN trained to steer a robot to follow a moving target. We identify possible
pitfalls of the conversion and demonstrate how the proposed solutions bring the
classification accuracy of the asynchronous network to only 3\% below the
performance of the original synchronous CNN, while requiring 12x fewer
computations. While being applied to a simple task, this work is an important
step towards low-power, fast, and embedded neural networks-based vision
solutions for robotic applications.

本文研究基于事件驱动的异步脉冲神经网络，并通过将经典的基于帧数据训练的卷积神经网络转换为异步网络，以在计算预算紧张的条件下实现低功耗、快速和嵌入式的神经网络视觉解决方案，其中应用范例是机器人跟踪移动目标。研究发现，异步网络的分类准确率仅比同步 CNN 低 3％，但计算量却减少了 12 倍。