[1]LIANG Hui,CAO Feng,QIAN Yuhua,et al.Number sequence logic learning in image context[J].CAAI Transactions on Intelligent Systems,2019,14(6):1189-1198.[doi:10.11992/tis.201905044]
Copy

Number sequence logic learning in image context

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 14 Number of periods: 2019 6 Page number: 1189-1198 Column: 学术论文—知识工程 Public date: 2019-11-05
Title:
Number sequence logic learning in image context
Author(s):
LIANG Hui1; 3;  CAO Feng1; 3;  QIAN Yuhua1; 2; 3;  GUO Qian1; 3;  LIANG Xinyan1; 3
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
Keywords:
artificial intelligence; logical reasoning; logical learning; deep learning; number sequences; image processing; neural network; pattern construction
CLC:
TP181
DOI:
10.11992/tis.201905044
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.
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.
Similar References:

Memo

-

Last Update: 2019-12-25

Copyright © CAAI Transactions on Intelligent Systems