Inductive Logic Programming - 32nd International Conference, ILP 2023, Bari, Italy, November 13-15, 2023, Proceedings
Inductive Logic Programming - 32nd International Conference, ILP 2023, Bari, Italy, November 13-15, 2023, Proceedings
复制标题
归纳逻辑编程 - 第 32 届国际会议，ILP 2023，意大利巴里，2023 年 11 月 13-15 日，会议记录
DOI：
10.1007/978-3-031-49299-0_12
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Cyrus D
中科院分区：
文献类型：
--
作者：
Cyrus D
分形图是几何图案，它们的每个组成部分都有相同的特征。它们被用来描述在更小的尺度上具有反复出现的模式的特征。本研究提供了一种基于元解释学习(MIL)的分形图像学习方法。多层卷积神经网络以前被用于从几何形状(例如规则多边形)中进行少量学习，并且与卷积神经网络(CNN)相比表现出明显更高的精度。我们的目标是说明MIL在从分形图像中学习中的应用。我们首先生成一个简单的分形图和非分形图的数据集，然后我们实现了一种学习描述分形图的递归规则的技术。我们的方法使用从图像中提取的图形作为背景知识。最后，我们对基于CNN的方法进行了评估，例如暹罗网络、VGG19、ResNet50和DenseNet169。
Fractals are geometric patterns with identical characteristics in each of their component parts. They are used to depict features which have recurring patterns at ever-smaller scales. This study offers a technique for learning from fractal images using Meta-Interpretative Learning (MIL). MIL has previously been employed for few-shot learning from geometrical shapes (e.g. regular polygons) and has exhibited significantly higher accuracy when compared to Convolutional Neural Networks (CNN). Our objective is to illustrate the application of MIL in learning from fractal images. We first generate a dataset of images of simple fractal and non-fractal geometries and then we implement a technique to learn recursive rules which describe fractal geometries. Our approach uses graphs extracted from images as background knowledge. Finally, we evaluate our approach against CNN-based approaches, such as Siamese Net, VGG19, ResNet50 and DenseNet169.