PROGRESSIVE LEARNING - UNIVERSAL CLASSIFIER
Research Aim
To integrate the progressive learning technique with the universal classifier, thereby achieving human-learning-inspired progressively learning universally generic classifier. The resulting new classifier can be used for binary, multi-class and multi-label classification problems with dynamic introduction of new classes.
​
Research Challenges
-
Identification of classification type
-
Estimating the number of target labels corresponding to each input sample
-
Identifying each of the associated target labels.
​​
Datasets
Binary: Diabetes, Ionosphere
Multi-class: Balance-scale, Satellite image, Digits
Multi-label: Scene, Yeast, Corel5k, Medical
​
Dataset specifications are given below:

Proposed Approach
The algorithm, code and datasets will be uploaded soon.
​
Results
The experimental results will be updated soon.
​