Dimensionality reduction in deep neural networks

• Main Author: Wee, Keane Jin Yen
• Other Authors: Chew Lock Yue
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Physics; Deep neural networks; Curse of dimensionality; Dimensionality reduction techniques; Explainability
• Online Access: https://hdl.handle.net/10356/184534
• Institution: Nanyang Technological University

Deep Neural Networks (DNNs) are powerful Artificial Intelligence (AI) techniques that enable machines to learn complex patterns from high-dimensional data. Due to the increasing complexity of data points and parameters in the model, DNNs experience the curse of dimensionality, where the model's...