N2MFn2: Non-negative Matrix Factorization in A Single Deconstruction Single Reconstruction Neural Network Framework for Dimensionality Reduction
Document Type
Conference Article
Publication Title
2022 International Conference on High Performance Big Data and Intelligent Systems, HDIS 2022
Abstract
One of the most commonly used approaches for handling complex datasets with high dimensions is dimension-Ality reduction. In this scenario, a single deconstruction single reconstruction neural network model for non-negative matrix factorization technique under neural network framework has been developed aiming towards low rank approximation. With the help of hierarchical learning, the pervasiveness of the non-negative input data has been processed to produce a part-based, sparse, and meaningful representation. A modification of the He initialization technique to initialize weights maintaining the non-negativity criteria of the model, has also been proposed. Necessary modification of the ReLU activation function has been made for inhibiting a layer's entire population of neurons from simultaneously adjusting their weights. Regularization has been used in the design of the model's objective function to minimize the risk of overfitting. To prove the competency of the proposed model, the results have been analyzed and compared with that of six other leading dimension reduction techniques on three popular datasets for classification. The analysis of the same has justified the effectiveness and superiority of the model over some others. Additionally the computational complexity of the model has been discussed.
First Page
79
Last Page
84
DOI
10.1109/HDIS56859.2022.9991646
Publication Date
1-1-2022
Recommended Citation
Dutta, Prasun and De, Rajat K., "N2MFn2: Non-negative Matrix Factorization in A Single Deconstruction Single Reconstruction Neural Network Framework for Dimensionality Reduction" (2022). Conference Articles. 427.
https://digitalcommons.isical.ac.in/conf-articles/427