Dimensionality reduction in deep neural networks

• المؤلف الرئيسي: Wee, Keane Jin Yen
• مؤلفون آخرون: Chew Lock Yue
• التنسيق: Final Year Project
• اللغة: English
• منشور في: Nanyang Technological University 2025
• الموضوعات: Physics; Deep neural networks; Curse of dimensionality; Dimensionality reduction techniques; Explainability
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/184534
• المؤسسة: 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...