UNIT 1:
Learning models: Geometric models –Probabilistic models –Logic models
Types of Learning – Supervised –Unsupervised – Reinforcement
Theory of learning –Feasibility of learning
Theory of Generalization –Generalization bound
Bias and variance –Learning Curve
Grouping and grading - Learning versus Design
Error and noise - Training versus Testing
Error and noise - Training versus Testing
UNIT 2:
Linear classification – Univariate Linear Regression
Support Vector Machines- Soft margin SVM
Perceptrons - Multilayer Neural Networks
Learning Neural Networks structures
UNIT 3:
K-means – Clustering around Medoids- Silhouttes
k-d trees –Locality Sensitive Hashing–
Bagging and random forests
Boosting –meta learning
K-means – Clustering around Medoids- Silhouttes
UNIT 4:
Trees –regression trees
Decision trees –learning decision trees
