Learning of human-like algebraic reasoning using deep feedforward neural networks | |
Cai, Cheng-Hao1; Xu, Yanyan2; Ke, Dengfeng3; Su, Kaile4 | |
刊名 | BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES |
2018-08-01 | |
卷号 | 25页码:43-50 |
关键词 | Reasoning-based learning Deep learning Algebraic reasoning Neural network reasoning |
ISSN号 | 2212-683X |
DOI | 10.1016/j.bica.2018.07.004 |
通讯作者 | Xu, Yanyan(xuyanyan@bjfu.edu.cn) |
英文摘要 | Human-like rewriting, which is an algebraic reasoning system imitating human intelligence of problem solving, is proposed in this work. In order to imitate both learning and reasoning aspects of human cognition, a deep feedforward neural network learns from algebraic reasoning examples produced by humans and then uses learnt experiences to guide other reasoning processes. This work shows that the neural network can learn human's behaviours of solving mathematical problems, and it can indicate suitable directions of reasoning, so that intelligent and heuristic reasoning can be performed. Moreover, human-like rewriting bridges the gap between symbolic reasoning and biologically inspired machine learning. To enable the neural network to recognise patterns of symbolic expressions with non-deterministic sizes, the expressions are reduced to partial tree representations and then vectorised as numeric features. Further, the centralisation method, symbolic association vectors and rule application records are used to improve the vectorised features. With these approaches, human-like rewriting shows satisfactory performance on the tasks of solving linear equations and computing derivations and indefinite integrals. |
资助项目 | Fundamental Research Funds for the Central Universities[2016JX06] ; National Natural Science Foundation of China[61472369] |
WOS关键词 | TERM REWRITING-SYSTEMS |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | ELSEVIER SCIENCE BV |
WOS记录号 | WOS:000447096500006 |
资助机构 | Fundamental Research Funds for the Central Universities ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/28118] |
专题 | 中国科学院自动化研究所 |
通讯作者 | Xu, Yanyan |
作者单位 | 1.Univ Auckland, Dept Comp Sci, 38 Princes St, Auckland 1142, New Zealand 2.Beijing Forestry Univ, Sch Informat Sci & Technol, 35 Qing Hua East Rd, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhong Guan Cun East Rd, Beijing 100190, Peoples R China 4.Griffith Univ, Inst Integrated & Intelligent Syst, 170 Kessels Rd, Nathan, Qld 4111, Australia |
推荐引用方式 GB/T 7714 | Cai, Cheng-Hao,Xu, Yanyan,Ke, Dengfeng,et al. Learning of human-like algebraic reasoning using deep feedforward neural networks[J]. BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES,2018,25:43-50. |
APA | Cai, Cheng-Hao,Xu, Yanyan,Ke, Dengfeng,&Su, Kaile.(2018).Learning of human-like algebraic reasoning using deep feedforward neural networks.BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES,25,43-50. |
MLA | Cai, Cheng-Hao,et al."Learning of human-like algebraic reasoning using deep feedforward neural networks".BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 25(2018):43-50. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论