The purpose of this course is to provide learners with a comprehensive foundation in Artificial Intelligence (AI) by examining its historical development, major concepts, techniques, applications, and emerging ethical considerations. The course introduces learners to both symbolic and data-driven approaches to AI, including knowledge representation, symbolic AI, neural networks, Convolutional Neural Networks (CNNs), Natural Language Processing (NLP), and Computer Vision, while developing an understanding of how AI systems can be designed and applied responsibly. Through theoretical discussions, practical activities, and coding exercises, learners develop the ability to analyse AI problems, select appropriate techniques, implement basic AI solutions, and critically evaluate their performance, limitations, and societal impact.

CLO 1: Describe the historical development of Artificial Intelligence and identify major milestones, approaches, and applications that have shaped the field.

CLO 2: Explain fundamental AI concepts, including intelligent agents, problem-solving, search, reasoning, learning, and decision-making.

CLO 3: Apply the principles of symbolic AI, CNNs, NLP, and Text Processing in problem solving.

CLO 4: Evaluate AI solutions based on their accuracy, effectiveness, limitations, computational requirements, and suitability for particular problems.

The course covers the history and evolution of Artificial Intelligence, introducing major developments from early symbolic approaches to modern machine-learning and deep-learning systems. It examines knowledge representation and symbolic AI, including logic, rules, inference, expert systems, and approaches for representing knowledge and reasoning. Learners are introduced to artificial neural networks and CNNs, exploring neurons, perceptrons, multi-layer networks, convolution, pooling, training, and image classification. The NLP component covers text preprocessing, tokenisation, N-grams, TF-IDF, embeddings, text classification, and sentiment analysis, while the Computer Vision component introduces image representation, image processing, feature extraction, object detection, and practical computer vision using OpenCV. The course concludes with Responsible AI, addressing fairness, bias, privacy, transparency, explainability, accountability, safety, and the social implications of AI. Practical coding projects and case studies are integrated throughout the course to enable learners to apply AI concepts to real-world problems.