N-MNIST (Neuromorphic-MNIST)

简要说明 Neuromorphic-MNIST (N-MNIST) 数据集是原始基于帧的 MNIST 数据集的尖峰版本。它由与原始 MNIST 数据集相同的 60 000 个训练样本和 10 000 个测试样本组成，并以与原始 MNIST 数据集（28x28 像素）相同的视觉比例捕获。 N-MNIST 数据集是通过将 ATIS 传感器安装在电动云台装置上并让传感器在 LCD 监视器上查看 MNIST 示例时移动来捕获的，如本视频所示。可以在下面的论文中找到对数据集及其创建方式的完整描述。如果您使用数据集，请引用本文。果园，G。科恩，G。贾亚万特，A。和 Thakor, N. “Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades”，《神经科学前沿》，第 9 卷，第 437 期，2015 年 10 月

A brief introduction: The Neuromorphic-MNIST (N-MNIST) dataset is the spiking variant of the original frame-based MNIST dataset. It consists of the same 60,000 training samples and 10,000 test samples as the original MNIST dataset, and is captured at the same visual scale as the original MNIST dataset (28×28 pixels). The N-MNIST dataset was captured by mounting an ATIS sensor on a motorized pan-tilt setup and moving the sensor while viewing MNIST examples on an LCD monitor, as shown in this video. A full description of the dataset and how it was created can be found in the following paper. Please cite this paper if you use the dataset. G. Orchard, G. Cohen, A. Jayawant, and N. Thakor: "Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades", Frontiers in Neuroscience, Vol. 9, Article 437, October 2015.

搜集汇总

背景与挑战

背景概述

N-MNIST数据集是原始MNIST数据集的尖峰神经形态版本，包含60,000个训练样本和10,000个测试样本，图像尺寸为28x28像素。它通过ATIS传感器在电动云台上移动捕获MNIST图像生成，专为尖峰神经网络研究设计，发布于2015年，采用CC BY-SA 4.0许可。