Update README.md

parent d95588ff
......@@ -3,10 +3,64 @@
## Main objective
Provide a novel post-hoc ,model-specific, local XAI solution to enhance the model interpretability of Black-Box models focus on
Random Forest, Support Vector Machine, K Nearest Neighbor and Logistic Regression by developing a novel counterfactual rule generation
mechanism related to the text classification domain.
## Main Research questions
## Individual research question
- IT20097660 | Sashini Devindi
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?
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 Random Forest classifier, when it becomes black box in
text classification?
- IT20013950 | Lakshani N.V.M.
How to get a counterfactual rule generation-based explanation for the k-NN classifier, when it handle Curse of Dimensionality
problem in text classification?
## Individual Objectives
## Other necessary information
\ No newline at end of file
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.
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 ensemble models focus
on Random forest by developing a novel counterfactual rule generation mechanism related to the text classification domain.
Provide a novel post-hoc ,model-specific, local XAI solution to enhance the model interpretability of distance-based classification
models focus on k-NN by developing a novel counterfactual rule generation mechanism related to the text classification domain.
## Other necessary information
Frontend:
- ReactJS
- Flask
- Boostrap
Backend:
- Python
Version Control:
- GitHub
Tools:
- VS Code
- Google Colab
Data set
- IMDB Dataset of 50K Movie Reviews
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment