This course provides a rigorous introduction to the fundamental principles and techniques of Machine Learning (ML), with an emphasis on intelligent decision-making, autonomous behaviour, and data-driven reasoning relevant to modern naval and defence applications. Designed for undergraduate naval officer training, the course develops both theoretical understanding and practical insight into how AI systems perceive environments, reason under uncertainty, learn from data, and support mission-critical decisions.
The course covers core ML paradigms, including problem formulation, state-space search, heuristic optimization, knowledge representation, and reasoning. It introduces machine learning concepts such as supervised and unsupervised learning, probabilistic models, and basic neural networks, enabling students to understand how intelligent systems adapt and improve performance over time. Special attention is given to AI techniques used in autonomous and semi-autonomous systems, including planning, perception, and real-time decision support.
Students will also explore applications of ML in areas relevant to naval operations, including autonomous vehicles, surveillance and reconnaissance, predictive analytics, and intelligent command-and-control systems. Ethical considerations, safety, robustness, and trustworthiness of AI systems in defense environments are discussed to develop responsible and informed future officers.
By the end of the course, students will be able to analyze AI-based solutions, understand their operational capabilities and limitations, and apply foundational AI concepts to solve practical problems in complex and dynamic environments.
This course provides an advanced and mathematically rigorous study of deep generative models for learning complex data distributions and generating novel, realistic, and controllable samples. It covers the fundamental principles, architectures, training methodologies, and theoretical foundations of modern generative AI. Topics include probabilistic generative modeling, autoregressive models, Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), normalizing flows, energy-based models, diffusion and score-based generative models, and flow matching. The course also examines the emergence of foundation and multimodal generative models, including their applications to text, images, audio, scientific data, and engineering systems.
Emphasis is placed on understanding the mathematical formulation, optimization objectives, sampling mechanisms, representation learning, conditioning, controllability, and evaluation of generative models. Students will critically analyze recent research, implement state-of-the-art generative architectures, and investigate issues related to generative quality, robustness, uncertainty, computational efficiency, interpretability, safety, and responsible AI. Through research-oriented assignments and projects, students will develop the ability to design, evaluate, and extend deep generative models for advanced research problems.
This course provides a comprehensive and rigorous introduction to text analysis, the field concerned with enabling computers to process, understand, and generate human languages. The course explores a wide range of computational methods for representing linguistic structure and meaning, and for designing intelligent systems that operate on text and speech data. Applications include machine translation, text summarization, sentiment analysis, information extraction, question answering, and conversational agents.
Text analysis is inherently multidisciplinary, drawing on ideas from machine learning, linguistics, probability theory, and artificial intelligence. Accordingly, this course integrates linguistic concepts with data-driven and learning-based approaches. Students will study computational representations of language at multiple levels, including words and subwords, phonetics and phonology, morphology, syntax, semantics, discourse, and dialogue. The interaction between these levels is emphasized to reflect how state-of-the-art NLP systems achieve robust performance on complex tasks.The course covers both classical and modern text analysis techniques, including n-gram language models, probabilistic sequence models, word embeddings, neural sequence models, attention mechanisms, and transformer-based architectures. Students will learn how large-scale text data and probabilistic modeling enable machines to capture linguistic regularities and semantic relationships. Special emphasis is placed on deep learning approaches that underpin contemporary NLP systems.
Through hands-on assignments, critical reading of research literature, and a research-oriented project, students will gain practical experience in building, evaluating, and analyzing NLP systems. By the end of the course, students will be able to understand and implement text analysis NLP algorithms, critically assess research contributions, and apply NLP techniques to real-world and research problems involving text and speech.
Natural Language Processing (Postgraduate) PNEC NUST
Deep Learning (Postgraduate) PNEC NUST
Artificial Intelligence (UTOs) PNEC NUST
Machine Learning (Postgraduate) PNEC NUST
Computational Techniques (Postgraduate) Abasyn University
Pattern recognition (Postgraduate) Abasyn University
Advanced Power Electronics (Postgraduate) PNEC NUST
Selected Topics in Power Systems (Postgraduate) PNEC NUST
Research Methodology (Postgraduate) Abasyn University
Power system stability and control (Undergraduate) CoEME NUST
Power System Analysis and Design (Undergraduate) CoEME NUST
Power Electronics (Undergraduate) CoEME NUST
Electronics devices and circuits (Undergraduate) CoEME NUST
Electrical Engineering (Undergraduate) CoEME NUST
Power Distribution and Utilization (Undergraduate) PNEC NUST