MACHINE LEARNING ALGORITHMS APPLIED ON THE KNOWLEDGE BASE OF AN ENDLESS LEARNING SYSTEM
Keywords:
machine learning, NELL systemAbstract
NELL is a never-ending learning system that aims to have computational systems learned in a continuous and incremental way, being also able to use acquired knowledge to improve their own learning. The objective of this work is to use different machine learning techniques to build models that make inferences and generate new facts in order to populate the knowledge base of the NELL system. The generated models were trained with a database built from information from existing relationships in the NELL knowledge base and compared through evaluation metrics that resulted in good prediction and classification values.
Downloads
References
Carlson, A. (2010). Toward na architecture for never-ending language learning. Proc. Ofthe Twenty-Fourth AAAI Conference on Artifical Intelligence.
dos Santos, E. B., Fernandes, M. L., Jr., E. R. H., and Duarte, M. C. (2016). Bayesiannetworks for identifying semantic relations in a never-ending learning system.
In Ma-dureira, A. M., Abraham, A., Gamboa, D., and Novais, P., editors,Intelligent SystemsDesign and Applications - 16th International Conference on Intelligent Systems Designand Applications (ISDA 2016) held in Porto, Portugal, December 16-18, 2016, volume557 ofAdvances in Intelligent Systems and Computing, pages 279–288. Springer.
Miani, R. G. L. and Junior, E. R. H. (2015). Exploring association rules in a large growingknowledge base.
Mitchell, T. (2015). Never-ending learning. Proceedings of the Conference on ArtificialIntelligence (AAAI).
Mitchell, T., Cohen, W., Hruschka, E., Talukdar, P., Yang, B., Betteridge, J., Carlson, A.,Dalvi, B., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohamed,T., Nakashole, N., Platanios, E., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya,D., Gupta, A., Chen, X., Saparov, A., Greaves, M., and Welling, J. (2018). Never-ending learning.Commun. ACM, 61(5):103–115.
Mitchell, T. M. (1997).Machine Learning. McGraw-Hill, New York.
Peter Norvig, S. R. (2013).Inteligˆencia Artificial. Elsevier Editora, third edition. ISBN8535237011, 9788535237016.
Thrun, S. and Mitchell, T. (1995). Lifelong robot learning.Robotics and AutonomousSystems, 15(1):25 – 46.
Thrun, S. and Pratt, L. (1998).Learning to Learn: Introduction and Overview, page 3–17.Kluwer Academic Publishers, USA.
Verma, S. and Hruschka, E. R. (2012). Coupled bayesian sets algorithm for semi-supervised learning and information extraction. InECML/PKDD.
