Hopkins Michael, Pineda-García Garibaldi, Bogdan Petruţ A, Furber Steve B
School of Computer Science, The University of Manchester, Oxford Road, Manchester M13 9PL, UK.
Interface Focus. 2018 Aug 6;8(4):20180007. doi: 10.1098/rsfs.2018.0007. Epub 2018 Jun 15.
State-of-the-art computer vision systems use frame-based cameras that sample the visual scene as a series of high-resolution images. These are then processed using convolutional neural networks using neurons with continuous outputs. Biological vision systems use a quite different approach, where the eyes (cameras) sample the visual scene continuously, often with a non-uniform resolution, and generate neural spike events in response to changes in the scene. The resulting spatio-temporal patterns of events are then processed through networks of spiking neurons. Such event-based processing offers advantages in terms of focusing constrained resources on the most salient features of the perceived scene, and those advantages should also accrue to engineered vision systems based upon similar principles. Event-based vision sensors, and event-based processing exemplified by the SpiNNaker (Spiking Neural Network Architecture) machine, can be used to model the biological vision pathway at various levels of detail. Here we use this approach to explore structural synaptic plasticity as a possible mechanism whereby biological vision systems may learn the statistics of their inputs without supervision, pointing the way to engineered vision systems with similar online learning capabilities.
最先进的计算机视觉系统使用基于帧的摄像头，这些摄像头将视觉场景采样为一系列高分辨率图像。然后使用具有连续输出的神经元的卷积神经网络对这些图像进行处理。生物视觉系统采用了一种截然不同的方法，眼睛（摄像头）以非均匀分辨率连续采样视觉场景，并响应场景变化生成神经脉冲事件。然后，通过脉冲神经元网络处理由此产生的时空事件模式。这种基于事件的处理在将有限资源集中于感知场景的最显著特征方面具有优势，并且这些优势也应适用于基于类似原理的工程视觉系统。基于事件的视觉传感器以及以SpiNNaker（脉冲神经网络架构）机器为例的基于事件的处理，可用于在不同细节层次上对生物视觉通路进行建模。在这里，我们使用这种方法来探索结构突触可塑性，作为生物视觉系统可能在无监督情况下学习其输入统计信息的一种可能机制，为具有类似在线学习能力的工程视觉系统指明方向。
