Course Description
This course introduces the fundamentals and advanced topics of pattern recognition for postgraduate students. It emphasizes both theory and applications of pattern recognition. Topics include overviews of general pattern recognition techniques, statistical decision theory, linear discriminant functions, multilayer neural networks, supervised learning, unsupervised learning and clustering, and applications of pattern recognition (such as biometrics and multimedia database retrieval.)
Intended Learning Outcomes
CILO-1: Evaluate the limitations of different classifiers and choose the appropriate approach for different scenarios of computer vision and pattern recognition.
CILO-2: Design and conduct experiments to evaluate the performance of different types of classifiers for computer vision and pattern recognition.
CILO-3: Apply pattern recognition, computer vision algorithms and mathematical models based on Python or Matlab for solving real-world applications.