PROJECT TITLE :

Transductive Multiview Modeling With Interpretable Rules, Matrix Factorization, and Cooperative Learning

ABSTRACT:

The goals of multiview fuzzy systems are to effectively deal with fuzzy modeling in multiview scenarios, as well as to acquire an interpretable model through the use of multiview learning. However, recent research on multiview fuzzy systems still faces a number of obstacles, one of which is the question of how to achieve effective collaboration between multiple views in situations where there is a limited amount of labeled data. This article investigates a novel transductive multiview fuzzy modeling approach in order to provide a solution to this problem. By incorporating transductive learning into the fuzzy model, it is possible to simultaneously learn both the model and the labels utilizing a novel learning criterion. This helps to reduce the dependency on data that has been labeled. In order to improve the performance of the fuzzy model even further, matrix factorization has been included. In addition to this, collaborative learning between multiple perspectives is utilized in order to increase the model's level of robustness. The findings of the experiments suggest that the proposed method can hold its own against other approaches to multiview learning.