@@ -10,6 +10,7 @@ mechanism related to the text classification domain.
## Main Research questions
- How to get a counterfactual rule generation-based explanation for the SVM, k-NN, Random Forest and Logistic Regression in text classification?
## Individual research question
...
...
@@ -18,7 +19,7 @@ mechanism related to the text classification domain.
How to get a counterfactual rule generation-based explanation for the Support Vector Machine classifier, when it handle non-linear separable data in text classification?
- #### IT18161298 | Srinidee
How to get a counterfactual rule generation-based explanation for the Logistic Regression classifier when it becomes black box in text classification?
How to get a counterfactual rule generation-based explanation for the Logistic Regression classifier, when it handles non-linear relationship or greater data complexity in text classification?
- #### IT20100698 | Thilini Anjalika
How to get a counterfactual rule generation-based explanation for the Random Forest classifier, when it becomes black box in text classification?
...
...
@@ -33,8 +34,7 @@ How to get a counterfactual rule generation-based explanation for the k-NN class
Provide a novel post-hoc ,model-specific, local XAI solution to enhance the model interpretability of function-based classification models focus on SVM by developing a novel counterfactual rule generation mechanism related to the text classification domain.
- #### IT18161298 | Srinidee
Providing model specific ,local ,post-hoc explanations using counterfactual mechanisms to improve the interpretability of the system.
Provide a novel post-hoc, model specific ,local XAI solution to enhance the model interpretability of binary logistic regression model forcus on LR by developing a novel counterfactual rule generation mechanism related to the text classificatio domain.
- #### IT20100698 | Thilini Anjalika
Provide a novel post-hoc ,model-specific, local XAI solution to enhance the model interpretability of ensemble models focus on Random forest by developing a novel counterfactual rule generation mechanism related to the text classification domain.
