ABSTRACT
Deep learning has made headlines in the past few years due to successes in tasks, such as self-driving vehicles and board games, which were previously thought difficult or impossible. The successes have generated much interest in artificial intelligence among researchers and members of the public. However, deep learning algorithms generally require very large labelled data sets to work well and large labelled data sets are not always readily available. In addition, most machine learning techniques, including deep learning, often perform well statistically but can fail miserably when, for example, data are deliberately perturbed in an adversarial attack. Another criticism of deep learning techniques is a relative lack of explainability. This paper proposes the use of intentional learning to simultaneously address these issues. Preliminary evaluation on the MNIST data set has shown promising results. Specifically, by combing extensional and intensional learning, it is possible to achieve similar accuracy result as extensional learning only using only one-sixth of the original training data set.
- Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (8 October 1986). "Learning representations by back-propagating errors". Nature. 323 (6088): 533--536Google ScholarCross Ref
- S. Hochreiter, Y. Bengio, P. Frasconi, and J. Schmidhuber. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In S. C. Kremer and J. F. Kolen, editors, A Field Guide to Dynamical Recurrent Neural Networks. IEEE Press, 2001Google Scholar
- LeCun, Y., Bengio, Y., and Hinton, G. 2015. "Deep learning". Nature. 521 (7553): 436--444Google ScholarCross Ref
- Goodfellow, I., Bengio, Y., and Courville, A. 2016. Deep Learning. MIT Press. ISBN 9780262035613Google Scholar
- Thrun, S. 2010. Toward Robotic Cars. Communications of the ACM. 53 (4): 99--106. doi:10.1145/1721654.1721679.Google ScholarDigital Library
- Daley S. 2018. AI Drones. https://builtin.com/artificial-intelligence/drones-ai-companiesGoogle Scholar
- Goldberg, Y. 2016. A Primer on Neural Network Models for Natural Language Processing. Journal of Artificial Intelligence Research. 57, 345--420Google ScholarDigital Library
- Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., and Kingsbury, B. 2012. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The shared views of four research groups. IEEE Signal Processing Magazine. 29 (6): 82--97. doi:10.1109/MSP.2012.2205597Google ScholarCross Ref
- Allen, J., Hunnicutt, M. S., Klatt, D. 1987. From Text to Speech: The MITalk system. Cambridge University Press. ISBN 978-0-521-30641-6.Google Scholar
- AlphaGo|DeepMind. https://deepmind.com/research/alphago/Google Scholar
- AI and Bias. IBM Research. https://www.research.ibm.com/5-in-5/ai-and-bias/Google Scholar
- Tho Q.T., Hui S.C., Fong A.C.M., and Cao T.H. 2006. Automatic fuzzy ontology generation for semantic web. IEEE Transactions on Knowledge and Data Engineering 18 (6), 842--856.Google ScholarDigital Library
- Tho Q.T., Hui S.C., Fong A.C.M., and Cao T.H. 2004. Automatic generation of ontology for scholarly semantic web. In Proceedings of the International Semantic Web Conference, 726--740.Google Scholar
- Tho Q.T., Hui S.C., and Fong A.C.M. 2006. Automatic fuzzy ontology generation for semantic help-desk support. IEEE Transactions on Industrial Informatics 2 (3), 155--164.Google ScholarCross Ref
- Fong A.C.M., Zhou B., Hui S.C., Tang J., and Hong G. 2012. Generation of personalized ontology based on consumer emotion and behavior analysis. IEEE Transactions on Affective Computing 3 (2), 152--164.Google ScholarDigital Library
- Huynh S.M., Parry D., Fong A.C.M., Tang J. 2014. Novel RFID and ontology-based home localization system for misplaced objects. IEEE Transactions on Consumer Electronics 60 (3), 402--410.Google ScholarCross Ref
- Missaoui, R., Valtchev, P., Djeraba, C., & Adda, M. 2007. Toward recommendation based on ontology-powered web-usage mining. IEEE Internet Computing, 11(4), 45--52.Google ScholarDigital Library
- Yang, S. Y. 2010. Developing an ontology-supported information integration and recommendation system for scholars. Expert Systems with Applications, 37(10), 7065--7079Google ScholarDigital Library
- Bonino, D., Corno, F., Farinetti, L., & Bosca, A. 2004. Ontology driven semantic search. WSEAS Transaction on Information Science and Application, 1(6), 1597--1605.Google Scholar
- MNIST data set. Available at https://www.nist.gov/itl/iad/image-group/emnist-dataset.Google Scholar
- Kaggle. Understanding Feature Engineering. https://www.kdnuggets.com/2018/03/understanding-feature-engineering-deep-learning-methods-text-data.htmlGoogle Scholar
- Efron, B.; Tibshirani, R. 1993. An Introduction to the Bootstrap. Boca Raton, FL: Chapman & Hall/CRC. ISBN 0-412-04231-2.Google Scholar
- Mikołajczyk A. and Grochowski M. 2018. Data augmentation for improving deep learning in image classification problem, 2018 International Interdisciplinary PhD Workshop (IIPhDW), Swinoujscie, pp. 117--122. doi: 10.1109/IIPHDW.2018.8388338Google Scholar
- Hyperopt. https://github.com/hyperopt/hyperoptGoogle Scholar
- Gini, C. 1909. Concentration and dependency ratios (in Italian). English translation in Rivista di Politica Economica, 87 (1997), 769--789.Google Scholar
- Rudolf W. Restructuring lattice theory: An approach based on hierarchies of concepts. 1982. Published in Rival, Ivan, ed. Ordered Sets. Proceedings of the NATO Advanced Study Institute held at Banff, Canada, August 28 to September 12, 1981. Nato Science Series C. 83. Springer Netherlands. pp. 445--470. doi:10.1007/978-94-009-7798-3.Google Scholar
- Pan S.J. and Yang Q. 2010. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering. 22(10), 1345--1359.Google ScholarDigital Library
- Chen Z. and Liu B. 2018. Lifelong machine learning. Morgan and Claypool. 207 Pages, August 2018.Google Scholar
Index Terms
- Ontology-Powered Hybrid Extensional-Intensional Learning
Recommendations
Deep learning: systematic review, models, challenges, and research directions
AbstractThe current development in deep learning is witnessing an exponential transition into automation applications. This automation transition can provide a promising framework for higher performance and lower complexity. This ongoing transition ...
Unsupervised and transfer learning challenge: a deep learning approach
UTLW'11: Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning workshop - Volume 27Learning good representations from a large set of unlabeled data is a particularly challenging task. Recent work (see Bengio (2009) for a review) shows that training deep architectures is a good way to extract such representations, by extracting and ...
Deep learning of representations for unsupervised and transfer learning
UTLW'11: Proceedings of the 2011 International Conference on Unsupervised and Transfer Learning workshop - Volume 27Deep learning algorithms seek to exploit the unknown structure in the input distribution in order to discover good representations, often at multiple levels, with higher-level learned features defined in terms of lower-level features. The objective is ...
Comments