Offered: Fall 2025 (current)
Introduction to pattern recognition: features, classifications, learning. Statistical methods, structural methods, and hybrid method. Applications to speech recognition, remote sensing, and biomedical area. Learning algorithms, Syntactic approach: Introduction to pattern grammars and languages. Parsing techniques. Pattern recognition in computer-aided design. Introduction to formal languages, String languages for pattern description, Higher dimensional pattern grammars, Syntax analysis as a recognition procedure, Stochastic languages, Error-corresponding parsing for string languages, Error-correcting tree automata, cluster analysis for syntactic patterns, Grammatical inference for syntactic approach to texture analysis.
The core objectives of this course are:
Build a foundation in syntactic pattern recognition, including formal language theory, grammar, and parsing techniques.
Work with syntactic pattern recognition for grammar induction, error-correcting parsing, and stochastic grammars.
Apply syntactic techniques to real-world problems in domains such as bioinformatics, medical imaging, robotics, and document analysis.
Integrate hybrid syntactic methods with statistical and neural approaches, such as deep learning and graph neural networks, to solve complex pattern recognition tasks by overcoming limitations of pure statistical and neural approaches.
Assess the ethical implications, scalability, and interpretability of syntactic pattern recognition systems.
Critically analyze recent advancements and open research problems in syntactic pattern recognition, preparing for future contributions to the field.
1. To Be Added
| # | Description | Weight | Edit |
|---|
