C4.5: programs for machine learning
C4.5: programs for machine learning
Induction of recursive transfer rules
Learning language in logic
Machine Learning
Transfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling
ECML '07 Proceedings of the 18th European conference on Machine Learning
On Universal Transfer Learning
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
KEEL: a software tool to assess evolutionary algorithms for data mining problems
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special Issue on Evolutionary and Metaheuristics based Data Mining (EMBDM); Guest Editors: José A. Gámez, María J. del Jesús, José M. Puerta
Supervised Machine Learning: A Review of Classification Techniques
Proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies
IEEE Transactions on Knowledge and Data Engineering
Integrating reinforcement learning with human demonstrations of varying ability
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Journal of Biomedical Informatics
Highly scalable and robust rule learner: performance evaluation and comparison
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
EDISC: A Class-Tailored Discretization Technique for Rule-Based Classification
IEEE Transactions on Knowledge and Data Engineering
Knowledge and Information Systems
| Hi-index | 0.00 |
Due to the rapid growth of computer technologies and the extensive changes in human needs, expertise and digital information were used to induce general conclusions. Such conclusions can be used to deal with future activates and make the life of humans easier. One active filed of machine learning that was developed for this purpose is inductive learning, and several families have emerged from this field. Specifically, RULES family was discovered as covering algorithm that directly induces good and general conclusions in the shape of simple rules. However, it was found that RULES suffer from two major deficiencies. It needs to tradeoff between time and accuracy when inducing the best rule and it did not appropriately handle incomplete data. As a result, this paper will present a new RULES algorithm, which takes advantage of previous versions of RULES family in addition to other advance methods of machine learning, specifically Transfer learning. Moreover, multi-modeling is also merged to transfer the knowledge of a different classification model and further improve the original algorithm. At the end, an empirical test is applied to compare the proposed algorithm with different single-model algorithms to prove that using the past knowledge of other agents in different domains improves specialization accuracy, whether the data is complete or incomplete.