Teaching & Education

Teaching Philosophy

My approach to education blends rigorous theoretical foundations with practical, hands-on implementation. I aim to cultivate critical thinking and problem-solving skills, preparing students not just to use AI tools, but to understand their underlying mechanics and innovate upon them.

• Experiential Learning

  Bridging theory and practice through real-world projects and coding assignments.

• Industry Relevance

  Updating curriculum with the latest advancements in Deep Learning and computer vision frameworks.

• Research-Led Teaching

  Integrating ongoing research challenges into classroom discussions to spark innovation.

Introduction to Programming (CS101)

Foundations of programming, algorithmic thinking, and problem-solving using Python/C++.

Data Structures & Algorithms (CS201)

Core data structures, algorithm analysis, sorting, and graph algorithms.

Database Management Systems (CS301)

Relational algebra, SQL, normalization, and modern NoSQL databases.

Machine Learning Fundamentals (CS401)

Supervised/unsupervised learning, linear models, decision trees, and model evaluation.

Artificial Intelligence (CS402)

Search algorithms, knowledge representation, expert systems, and AI applications.

Computer Vision Lab (CS501L)

Hands-on implementation of image processing and CNN models using OpenCV and PyTorch.

Advanced Machine Learning (MCS501)

Ensemble methods, probabilistic graphical models, and advanced optimization.

Deep Learning & Neural Networks (MCS502)

RNNs, Transformers, Generative Adversarial Networks (GANs), and cutting-edge architectures.

Research Methodology (MCS503)

Literature review, experimental design, technical writing, and ethics in AI research.

Advanced Computer Vision (MCS601)

3D vision, video analysis, state-of-the-art object detection (YOLOv8/v10), and segmentation.