返回
Multi-granulation Multi-scale Relation Network for Abstract Reasoning
DOI:10.1007/s13042-021-01484-5.png)
摘要
En 中文
A Abstract reasoning, one of the representative works of logic learning, is to make machines intelligent. To test the intelligence of machines, researchers have proposed multiple benchmark data sets and these date sets mainly consist of a few simple geometries and traced reasoning paths. There are three issues for these data sets: (1) it is relatively easy for machines to reason the right answer from the simple geometries; (2) due to the limited number of geometric shapes, these data sets are prone to disclosure of information about reasoning; (3) all traced reasoning paths in these data sets have been known beforehand, some state-of-the-art reasoning models are specially designed according to these paths. Hence, these benchmark data sets cannot truly reflect the reasoning ability of reasoning models. To address these issues, we propose a Fashion Non-descending Path data set (FNP). FNP is designed using a mass of complex samples from Fashion-MNIST data set as objects of FNP and the non-descending path that is a more complex path as the variation directions of logical patterns. For gaining reasoning performance on FNP, inspired by the multi-granulation and multi-scale ideas, we propose a multi-granulation multi-scale relation network (M2RN) to consider the multi-wise relations rather than the simple pair-wise relations. Experimental results show that the M2RN is effective for abstract reasoning task.
Keyword:
Multi-granulation
Multi-scale
Non-descending path
Abstract reasoning
Relation network
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
Evolutionary Deep Fusion Method and its Application in Chemical Structure Recognition进化深度融合方法及其在化学结构识别中的应用
Tocilizumab Successfully Treating Refractory Hearing Impairment in a Patient With Cogan Syndrome: A Case Report and Review of the Literature托珠单抗成功治疗考根综合征患者难治性听力障碍:1例病例报告及文献综述

