Syllabus

1. Pattern Recoginiton- overview, Types of Pattern Recognition, Feature extraction-Statistical Pattern Recognition-Supervised & Unsupervised Learning Bayes decision Theory, Linear discriminant functions.

2. Parametric methods- ML & MAP estimation, Bayesian estimation, Non Parametric methods- Density estimation, Parzen Windows, Probabilistic Neural Networks (PNNs).

3. Unsupervised clustering- Tree clustering- K-means clustering,

4. Linear models for classification and regression: Linear Discriminant Functions, Perceptron-Learning Algorithm and convergence proof, Linear Least Squares Regression LMS algorithm,

5. Model free technique – ROC Curve, Classifier evaluation, Back propagation learning, Competitive learning

To gain an understanding of pattern recognition systems and statistical tools used in implementing pattern recognition systems.

To understand the usage of different pattern recognition systems

To gain skills for developing pattern recognition systems for healthcare applications.

After completing the course, the students will able to
1. Understand and apply mathematical concepts required for foundational understanding of pattern recognition.
2. Understand different modules/steps involved in the development of pattern recognition systems.
3. Use mathematical concepts for in-depth analysis and exploration of data in the context of pattern recognition.
4. Learn to use state-of-the-art tools and methods for development of pattern recognition systems.
5. Conceptualise and design pattern recognition systems for complex tasks related to healthcare applications while keeping in mind ethical requirements related to healthcare applications.

Duda R O, Hart P E, and Stork D G, Pattern classification, John Wiley and Sons

Christopher M B, Pattern Recognition and Machine Learning, Springer

Robert Schalkoff, Pattern recognition, Statistical, Structural and neural approaches, John Wiley and Sons

Fu K S, Syntactic Pattern recognition and applications, Prentice Hall