About this course
This course provides a comprehensive introduction to the core concepts underpinning intelligent systems. You will explore the principles of Machine Learning, including supervised, unsupervised, and reinforcement learning. Delve into Deep Learning and the power of neural networks. Understand how machines represent and reason with knowledge through Knowledge Representation and Reasoning (KRR), logic-based systems, and expert systems. Finally, the course examines the critical aspects of Explainable AI (XAI), cognitive architectures, knowledge graphs, and the societal impact of AI, culminating in understanding the complete AI lifecycle.
Comments (0)
Define Machine Learning and understand its types (Supervised, Unsupervised, Reinforcement).
Define Deep Learning and explore how neural networks learn complex patterns from data.
Define Knowledge Representation (KR) and Knowledge Representation and Reasoning (KRR) in machines.
Understand the fundamental principles of logic-based Knowledge Representation and inference.
Define Expert Systems and identify key components like knowledge base and inference engine.
Understand how reasoning is integrated into machine learning to explain predictions and decisions.
Understand what cognitive architectures are and how they simulate human-like intelligence in AI systems.
Examine the need for explainability in AI and techniques used to interpret model outputs.
Understand the structure and use of knowledge graphs for organizing and connecting data in AI.
Implement a digit recognition model using Python and understand the basics of image-based AI tasks.
Evaluate the advantages and limitations of AI in society, education, healthcare, and industry.
Explore the complete AI lifecycle from problem definition to deployment and maintenance of models.
