Syllabus
|
Course Code: *Elective –I MTEC-107 Course Name: Pattern Recognition and Machine Learning |
||
| MODULE NO / UNIT | COURSE SYLLABUS CONTENTS OF MODULE | NOTES |
|---|---|---|
| 1 | Introduction to Pattern Recognition: Problems, applications, design cycle, learning andadaptation, examples, Probability Distributions, Parametric Learning - Maximum likelihood and Bayesian Decision Theory- Bayes rule, discriminant functions, loss functions and Bayesian error analysisLinear models: Linear Models for Regression, linear regression, logistic regression LinearModels for Classification | |
| 2 | Neural Network: perceptron, multi-layer perceptron, backpropagation algorithm, error surfaces,practical techniques for improving backpropagation, additional networks and training methods, Adaboost, Deep Learning | |
| 3 | Linear discriminant functions - decision surfaces, two-category, multi-category, minimum-squared error procedures, the Ho-Kashyap procedures, linear programming algorithms, Support vector machine | |
| 4 | Algorithm independent machine learning – lack of inherent superiority of any classifier, biasand variance, resampling for classifier design, combining classifiers Unsupervised learning and clustering – k-means clustering, fuzzy k-means clustering,hierar chical clustering |
|
