Skimming Digits: Neuromorphic Classification of Spike-Encoded Images
Skimming Digits: Neuromorphic Classification of Spike-Encoded Images
复制标题
DOI：
10.3389/fnins.2016.00184
复制
发表时间：
2016-04-28
影响因子：
4.3
通讯作者：
van Schaik, Andre
中科院分区：
文献类型：
--
作者：
Cohen, Gregory K.;Orchard, Garrick;van Schaik, Andre
对计算机视觉领域日益增长的需求重新关注替代视觉场景表示和处理范式。硅视网膜提供了一种替代的手段成像的视觉环境，并产生无帧时空数据。本文提出了一种基于事件的数字分类使用N-MNIST，一个神经形态数据集创建的硅视网膜，和突触核逆方法（SKIM），学习方法的基础上树突计算的原则。由于这项工作代表了使用SKIM网络执行的第一个大规模和多类分类任务，因此它探索了扩展原始SKIM方法以支持多类问题所需的不同训练模式和输出确定方法。利用SKIM网络应用于真实世界的数据集，实现最大的隐藏层大小，同时训练最大数量的输出神经元，分类系统在包含10，000个隐藏层神经元的网络中实现了92.87%的最佳情况准确率。这些结果代表了迄今为止对数据集实现的最高精度，并用于验证SKIM方法在基于事件的视觉分类任务中的应用。此外，研究发现，使用方波脉冲作为监督训练信号对于大多数输出确定方法来说可以产生最高的准确度，但结果也表明指数模式更适合硬件实现，因为它利用了最简单的输出确定方法基于最大值。
The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value.