Grammar-based Fuzzy Pattern Trees for Classification Problems

Murphy, Anthony; Ali, Muhammad; Dias, Douglas Mota; Amaral, Jorge; Naredo, Enrique; Ryan, Conor

doi:10.5220/0010111900710080

Cited by 6 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GE was recently introduced as a method to evolve Fuzzy Pattern Trees [22]. This approach, named Fuzzy Grammatical Evolution, was shown to produce competitive performance compared with state of the art black box methods and exceeded the performance of another GP variant, Cartesian GP, on a set of benchmark classification problems [34].…”

Section: Fuzzy Gementioning

confidence: 99%

“…For instance if a problem had 3 classes we need to create 3 Fuzzy Pattern Trees, FT 1 , FT 2 and FT 3 . If FT 1 has an output of 0.2, FT 2 an output of 0.6 and FT 3 an output of 0.3 for a particular instance, then the WTA function will assign this instance as class 2, as it has the highest score GE may be bloating individuals, yielding trees which are excessively large and contain worthless material [22]. The addition of a simple parsimony pressure was seen to greatly reduce the size of individuals without having a noticeable effect on their fitness.…”

Section: Fuzzy Gementioning

confidence: 99%

“…In the previous experiments [22], the continuous data for each benchmark was partitioned into three fuzzy sets; Low, Medium and High. Each set had either a linear (Low and High) or triangular (Medium) membership function and the values for the limits of the membership functions were based on the distribution of the input data.…”

Section: Designing Fuzzy Partitionsmentioning

confidence: 99%

“…complexity and size not being extremely large. Grammatical Evolution has been shown to be a very efficient and effective approach for evolving accurate, and, vitally, small Fuzzy Pattern Trees [22].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Human in the Loop Fuzzy Pattern Tree Evolution

Murphy

Dias

et al. 2022

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

Fuzzy pattern trees evolved using grammatical evolution, a system we call Fuzzy Grammatical Evolution, are shown to be a robust Explainable Artificial Intelligence technique. Experimental results show Fuzzy Grammatical Evolution achieves competitive results when compared against SVM, Random Forest and Logistic Regression on a set of real world benchmark problems. Fuzzy Grammatical Evolution allows for human input throughout the evolutionary process. Regularization methods and double tournament selection were investigated to determine what method was most successful at finding smaller, more interpretable models. A domain expert was recruited to investigate the interpretability of the models found and to give a confidence score for each model. This expert successfully identified overfit models, validating that Fuzzy Grammatical Evolution can be regarded a powerful Explainable Artificial Intelligence technique.

show abstract

Section: Fuzzy Gementioning

confidence: 99%

Section: Fuzzy Gementioning

confidence: 99%

Section: Designing Fuzzy Partitionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human in the Loop Fuzzy Pattern Tree Evolution

Murphy

Dias

et al. 2022

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is an extended version of a paper published in the proceedings of the 12th International Conference on Evolutionary Theory and Applications [ 25 ]. The previous work is built upon by investigating the effects various ensemble methods have on the performance of the classifiers.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Pattern Tree Evolution Using Grammatical Evolution

et al. 2022

Self Cite

View full text Add to dashboard Cite

A novel approach to induce Fuzzy Pattern Trees using Grammatical Evolution is presented in this paper. This new method, called Fuzzy Grammatical Evolution, is applied to a set of benchmark classification problems. Experimental results show that Fuzzy Grammatical Evolution attains similar and oftentimes better results when compared with state-of-the-art Fuzzy Pattern Tree composing methods, namely Fuzzy Pattern Trees evolved using Cartesian Genetic Programming, on a set of benchmark problems. We show that, although Cartesian Genetic Programming produces smaller trees, Fuzzy Grammatical Evolution produces better performing trees. Fuzzy Grammatical Evolution also benefits from a reduction in the number of necessary user-selectable parameters, while Cartesian Genetic Programming requires the selection of three crucial graph parameters before each experiment. To address the issue of bloat, an additional version of Fuzzy Grammatical Evolution using parsimony pressure was tested. The experimental results show that Fuzzy Grammatical Evolution with this extension routinely finds smaller trees than those using Cartesian Genetic Programming without any compromise in performance. To improve the performance of Fuzzy Grammatical Evolution, various ensemble methods were investigated. Boosting was seen to find the best individuals on half the benchmarks investigated.

show abstract

Towards Incorporating Human Knowledge in Fuzzy Pattern Tree Evolution

Murphy

Amaral

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Grammar-based Fuzzy Pattern Trees for Classification Problems

Cited by 6 publications

References 0 publications

Human in the Loop Fuzzy Pattern Tree Evolution

Human in the Loop Fuzzy Pattern Tree Evolution

Fuzzy Pattern Tree Evolution Using Grammatical Evolution

Towards Incorporating Human Knowledge in Fuzzy Pattern Tree Evolution

Contact Info

Product

Resources

About