Comprehensive introduction to machine learning with strong emphasis on PyTorch implementation and deep understanding of fundamental algorithms. The curriculum follows a systematic progression from basic statistical learning methods to advanced neural network architectures, with particular focus on understanding and implementing backpropagation from the ground up.
Advanced machine learning course covering cutting-edge ML algorithms, their implementation, and practical applications in addressing real-world challenges. Focus on machine learning models for high-dimensional and complex data where traditional deterministic methods often fall short.
Ph.D. in Computer Science • 2023-2025 • Completed
Dissertation: "Advanced Deep Learning Techniques for Infrastructure Defect Detection and Segmentation"
Research focused on developing state-of-the-art neural network architectures for automated inspection of culverts and sewer systems, including imbalance-aware segmentation, attention mechanisms, and dual-attentive U-Net architectures.
M.S. in Computer Science • 2024-Present • In Progress
Thesis: "Machine Learning Applications in Infrastructure Monitoring and Predictive Maintenance"
Research involves developing intelligent systems for real-time infrastructure health monitoring using computer vision and IoT sensors. Focus on edge computing solutions for resource-constrained environments.
Ph.D. Student, Nanyang Technological University • 2022-2024
Research on explainable few-shot learning in remote sensing. Co-authored publications in Artificial Intelligence Review (IF: 10.7) and IEEE/CVF WACV.
Ph.D. Student, Nanyang Technological University • 2021-2023
Research on adversarial learning and continual learning. Co-authored 6+ publications in ACM CIKM, IEEE ICIP, and ECML-PKDD.
Graduate Research Assistant, University of New Orleans • 2024-Present
Research on physics-regularized machine learning for oceanic parameter forecasting using multi-hyperparameter optimization.
Visiting Scholar, Graz University of Technology • 2024-Present
Research on FORTRESS framework for real-time resilient structural segmentation using Kolmogorov-Arnold enhanced networks.
Ph.D. Student, UNSW Australia • 2023-Present
Research on adaptive spectral and self-supervised learning for wind power forecasting using CNN-LSTM architectures.