利用 SpinalNet 进行星系的形态分类（英文版）

英文标题：Morphological Classification of Galaxies Using SpinalNet中文摘要：本文介绍了 SpinalNet 这种类似于人体远感系统的深度神经网络，其输入分割使得中间层能够接收前一层的一些输入和输出，从而减少了中间层的权重，使得计算成本和误差都大幅降低，应用于 Galaxy Zoo 数据集的分类准确率得到了进一步提升，分别为 98.2％，95％和 82％。英文摘要：Deep neural networks (DNNs) with a step-by-step introduction of inputs, whichis constructed by imitating the somatosensory system in human body, known asSpinalNet have been implemented in this work on a Galaxy Zoo dataset. The inputsegmentation in SpinalNet has enabled the intermediate la