[1]梁慧,曹峰,钱宇华,等.图像情境下的数字序列逻辑学习[J].智能系统学报,2019,14(06):1189-1198.[doi:10.11992/tis.201905044]
 LIANG Hui,CAO Feng,QIAN Yuhua,et al.Number sequence logic learning in image context[J].CAAI Transactions on Intelligent Systems,2019,14(06):1189-1198.[doi:10.11992/tis.201905044]
点击复制

图像情境下的数字序列逻辑学习(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年06期
页码:
1189-1198
栏目:
出版日期:
2019-11-05

文章信息/Info

Title:
Number sequence logic learning in image context
作者:
梁慧13 曹峰13 钱宇华123 郭倩13 梁新彦13
1. 山西大学 大数据科学与产业研究院, 山西 太原 030006;
2. 山西大学 计算智能与中文信息处理教育部重点实验室, 山西 太原 030006;
3. 山西大学 计算机与信息技术学院, 山西 太原 030006
Author(s):
LIANG Hui13 CAO Feng13 QIAN Yuhua123 GUO Qian13 LIANG Xinyan13
1. Research Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China;
2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006, China;
3. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China
关键词:
人工智能逻辑推理逻辑学习深度学习数字序列图像处理神经网络模式构建
Keywords:
artificial intelligencelogical reasoninglogical learningdeep learningnumber sequencesimage processingneural networkpattern construction
分类号:
TP181
DOI:
10.11992/tis.201905044
摘要:
针对未知的数字和规则的模式构建问题,本文提供了一种从图像角度解决数字序列逻辑学习问题的手段。该方法是在计算机不知道图像间关系和图像内包含的内容的意义的前提下,让计算机自主地学习出其中包含的内在逻辑模式,从而进行数字序列的预测。本文构建了4个大型数据集:Linear序列、Multiplication序列、Fio序列和Nested序列,然后使用几种代表性的深度神经网络来完成数字序列逻辑学习任务,并对实验结果加以分析比较,事实证明,本文所提出的方法在一定程度上可以解决未知的数字和规则的模式构建问题,这为一系列未知逻辑模式构建任务提供了一种可能性。
Abstract:
To solve the problem of pattern construction of unknown numbers and rules, in this paper, we provide a method to solve the problems of number sequence logic learning from the image perspective. The method allows the computer to automatically learn the inherent logic pattern without prior knowledge of the meaning of the image content or of the relationship between images so as to predict the number sequence. Four large datasets were constructed: linear sequences, multiplication sequences, fio sequences, and nested sequences, and then several representative deep neural networks were used to complete the number sequence logic learning task. By analyzing the experimental results, the method was found capable of solving the problem of pattern construction for unknown numbers and rules to a certain extent, which will provide a potential solution for a series of unknown logic pattern construction tasks.

参考文献/References:

[1] BOGOSHI J. The oldest mathematical artefact[J]. The mathematical gazette, 1987, 71(458):294-294.
[2] SCHMID U, KITZELMANN E. Inductive rule learning on the knowledge level[J]. Cognitive systems research, 2011, 12(3/4):237-248.
[3] FLENER P, SCHMID U. An introduction to inductive programming[J]. Artificial intelligence review, 2008, 29(1):45-62.
[4] COLTON S, BUNDY A, WALSH T. Automatic Invention of Integer Sequences[M]//The fertility of the soil/. Cambridge University Press AAAI/IAAI, 2000:558-563.
[5] QIAN Y, LI F J, LIANG J Y, et al. Space structure and clustering of categorical data[J]. IEEE transactions on neural networks and learning systems, 2016, 27(10):2047-2059.
[6] QIAN Y, XU H, LIANG J Y, et al. Fusing monotonic decision trees[J]. IEEE transactions on knowledge and data engineering, 2015, 27(10):2717-2728.
[7] QIAN Y, LI Y, LIANG J, et al. Fuzzy granular structure distance[J]. IEEE transactions on fuzzy systems, 2015, 23(6):2245-2259.
[8] QIAN Y, LIANG J, PEDRYCZ W, et al. Positive approximation:An accelerator for attribute reduction in rough set theory[J]. Artificial intelligence, 2010, 174(9/10):597-618.
[9] RAVEN J, et al. Raven progressive matrices[M]. Handbook of Nonverbal Assessment, 2003, 223-237.
[10] MUGGLETON S, CHEN J. Guest editorial:special issue on inductive logic programming (ILP 2011)[J]. Machine learning, 2012, 89(3):213-214.
[11] HOLZMAN T G, PELLIGRINO J W, GLASER R. Cognitive dimensions of numerical rule induction[J]. Journal of educational psychology, 1982, 74(3):360-373.
[12] STERNBERG R.J. Handbook of Intelligence[M]. Cambridge University Press, 2000.
[13] SIMON H A, KOTOVSKY K. Human acquisition of concepts for sequential patterns[J]. Psychological review, 1963, 70(6):534-546.
[14] SANGHI P, DOWE D.L, A computer program capable of passing I.Q. tests[C]//4th Int. Conf. on Cognitive Science(ICCS’03), Sydney, 2003:570-575.
[15] SIEBERS M, SCHMID U. Semi-analytic natural number series induction[J]. Advances in artificial intelligence, 2012, 7526:249-252.
[16] STRANNEGARD C, AMIRGHASEMI M, ULFSBACKER S. An anthropomorphic method for number sequence problems[J]. Cognitive systems research, 2013, 22-23:27-34.
[17] HOFMANN J, KITZELMANN E, SCHMID U. Applying inductive program synthesis to induction of number series a case study with IGOR2[J]. Joint german/austrian conference on artificial intelligence(Künstliche Intelligenz).Springer, Cham, 2014:25-36.
[18] RAGNI M, KLEIN A. Predicting numbers:An AI approach to solving number series[C]//German Conference on Advances in Artificial Intelligence. Springer, Berlin, Heidelberg, 2011:255-259.
[19] RAGNI M, KLEIN A. Solving number series-architectural properties of successful artificial neural networks[C]//NCTA 2011-Proceedings of the International Conference on Neural Computation Theory and Applications, 2011:224-229.
[20] KINGMA D P, BA J. Adam:A method for stochastic optimization.[C]//Proceedings of the 3rd International Comference on Learning Representations, San Diego, arXiv prerint arXiv:1412.6980, 2014.
[21] LECUN Y, BENGIO Y, Hinton G. Deep learning[M]. Nature, 2015, 521(7553):436.
[22] HOCHREITER S, SCHMIDHUBER, JüRGEN. Long short-term memory[J]. Neural computation, 1997, 9(8):1735-1780.
[23] CHUMERIN N. Convolutional neural network[J]. Neurocomputing, 2015, 148:136-142.
[24] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. In:advances in neural information processing systems, 2012:1097-1105.
[25] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of machine learning research, 2014, 15(1):1929-1958.
[26] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[J]. In proceedings of the IEEE conference on computer vision and pattern recognition, 2016:770-778.
[27] SMITH R. An overview of the tesseract OCR engine[C]//icdar. IEEE Computer Society, 2007, 2:629-633.

相似文献/References:

[1]李德毅.网络时代人工智能研究与发展[J].智能系统学报,2009,4(01):1.
 LI De-yi.AI research and development in the network age[J].CAAI Transactions on Intelligent Systems,2009,4(06):1.
[2]赵克勤.二元联系数A+Bi的理论基础与基本算法及在人工智能中的应用[J].智能系统学报,2008,3(06):476.
 ZHAO Ke-qin.The theoretical basis and basic algorithm of binary connection A+Bi and its application in AI[J].CAAI Transactions on Intelligent Systems,2008,3(06):476.
[3]徐玉如,庞永杰,甘 永,等.智能水下机器人技术展望[J].智能系统学报,2006,1(01):9.
 XU Yu-ru,PANG Yong-jie,GAN Yong,et al.AUV—state-of-the-art and prospect[J].CAAI Transactions on Intelligent Systems,2006,1(06):9.
[4]王志良.人工心理与人工情感[J].智能系统学报,2006,1(01):38.
 WANG Zhi-liang.Artificial psychology and artificial emotion[J].CAAI Transactions on Intelligent Systems,2006,1(06):38.
[5]赵克勤.集对分析的不确定性系统理论在AI中的应用[J].智能系统学报,2006,1(02):16.
 ZHAO Ke-qin.The application of uncertainty systems theory of set pair analysis (SPU)in the artificial intelligence[J].CAAI Transactions on Intelligent Systems,2006,1(06):16.
[6]秦裕林,朱新民,朱 丹.Herbert Simon在最后几年里的两个研究方向[J].智能系统学报,2006,1(02):11.
 QIN Yu-lin,ZHU Xin-min,ZHU Dan.Herbert Simons two research directions in his lost years[J].CAAI Transactions on Intelligent Systems,2006,1(06):11.
[7]谷文祥,李 丽,李丹丹.规划识别的研究及其应用[J].智能系统学报,2007,2(01):1.
 GU Wen-xiang,LI Li,LI Dan-dan.Research and application of plan recognition[J].CAAI Transactions on Intelligent Systems,2007,2(06):1.
[8]杨春燕,蔡 文.可拓信息-知识-智能形式化体系研究[J].智能系统学报,2007,2(03):8.
 YANG Chun-yan,CAI Wen.A formalized system of extension information-knowledge-intelligence[J].CAAI Transactions on Intelligent Systems,2007,2(06):8.
[9]赵克勤.SPA的同异反系统理论在人工智能研究中的应用[J].智能系统学报,2007,2(05):20.
 ZHAO Ke-qin.The application of SPAbased identicaldiscrepancycontrary system theory in artificial intelligence research[J].CAAI Transactions on Intelligent Systems,2007,2(06):20.
[10]王志良,杨 溢,杨 扬,等.一种周期时变马尔可夫室内位置预测模型[J].智能系统学报,2009,4(06):521.[doi:10.3969/j.issn.1673-4785.2009.06.009]
 WANG Zhi-liang,YANG Yi,YANG Yang,et al.A periodic time-varying Markov model for indoor location prediction[J].CAAI Transactions on Intelligent Systems,2009,4(06):521.[doi:10.3969/j.issn.1673-4785.2009.06.009]

备注/Memo

备注/Memo:
收稿日期:2019-04-15。
基金项目:国家自然科学基金项目(61672332,61432011,U1435212,61872226);山西省海外归国人员研究项目(2017023);山西省自然科学基金计划资助项目(201701D121052)
作者简介:梁慧,女,1994年生,硕士研究生,主要研究方向为机器学习、深度学习和逻辑学习;曹峰,男,1980年生,副教授,博士,主要研究方向为人工智能、空间数据挖掘。主持国家自然科学青年基金项目1项,山西省青年科技研究基金项目1项,参与山西省青年科技研究基金项目2项,获中国科学院大学优秀毕业生称号,博士论文被评为中国科学院地理科学与资源研究所优秀博士论文。发表学术论文10余篇;钱宇华,男,1976年生,教授,博士生导师,主要研究方向为人工智能、大数据、复杂网络、数据挖掘与机器学习。2014-2016年,连续入选爱思唯尔中国高被引学者榜单。曾获得山西省科学技术奖(自然科学类)一等奖,教育部宝钢教育基金特等奖,CCF优秀博士论文奖,山西省"五四青年奖章",全国百篇优秀博士论文提名奖,获发明专利2项。发表学术论文80余篇
通讯作者:钱宇华.E-mail:jinchengqyh@126.com
更新日期/Last Update: 2019-12-25