We present an optimization-based theory describing spiking cortical ensembles equipped with Spike-Timing-Dependent Plasticity (STDP) learning, as empirically observed in the visual cortex. Using our methods, we build a class of fully-connected, convolutional and action-based feature descriptors for event-based camera that we respectively assess on N-MNIST, challenging CIFAR10-DVS and on the IBM DVS128 gesture dataset. We report significant accuracy improvements compared to conventional state-of-the-art event-based feature descriptors (+8% on CIFAR10-DVS). We report large improvements in accuracy compared to state-of-the-art STDP-based systems (+10% on N-MNIST, +7.74% on IBM DVS128 Gesture). In addition to ultra-low-power learning in neuromorphic edge devices, our work helps paving the way towards a biologically-realistic, optimization-based theory of cortical vision.
翻译:我们提出了一个基于优化的理论,描述了在视觉皮层中亲眼观察到的带有斯派丁-依赖性可塑性(STDP)特征描述器(STDP)的学习。我们用我们的方法,为以事件为基础的照相机建造了一套完全连接的、革命性的和基于行动的特征描述器,我们分别对N-MNIST、挑战性的CIFAR10-DVS和IBM DVS128手势数据集进行了评估。我们报告说,与以事件为基础的常规状态特征描述器(CIFAR10-DVS+8%)相比,精确度有了显著提高。 我们报告,与以现代STDP为基础的系统(N-MNIST,+10%,IBM DVS128 Gesture)相比,精确度有了很大的提高。 除了在神经形态边缘装置中进行超低功率学习外,我们的工作还帮助铺平了通往以生物现实和优化为基础的视觉理论的道路。