Abstract:
Feature selection eliminates unimportant features. Embedded feature selection methods, which learn feature weights during classifier training, have garnered attention recently. Traditional embedded methods only optimize all features combinatorially. They sometimes select weakly relevant features with good combination abilities and leave out strongly relevant features, degrading generalization performance. Feature selection boosted by unselected features (FSBUF) is a new embedded framework for feature selection that addresses this issue. We add an unselected feature classifier to the traditional embedded model and jointly learn feature weights to maximize classification loss. The extra classifier recycles unselected strongly relevant features to replace weakly relevant features in the selected feature subset. We use a gradient-based algorithm to solve our final minimax optimization problem. We theoretically prove that the proposed FSBUF improves the generalization ability of traditional embedded feature selection methods. Extensive experiments on synthetic and real-world data sets demonstrate FSBUF’s clarity and performance.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
