Announcements

Syllabus

• Introduction to real world signals - text, speech, image, video.
• Feature extraction and dimensionality reduction - principal components, linear discriminants.
• Decision theory for pattern recognition, ML and MAP methods, Bias-variance trade-off, model assessment, cross-validation, estimating generalization error.
• Generative modeling and density estimation - Gaussian and mixture Gaussian models, kernel density estimators, hidden Markov models. Expectation Maximization.
• Linear regression and kernel methods. Regularization methods.
• Discriminative modeling - support vector machines, decision trees and random forest classifiers, bagging and boosting.
• Neural networks: gradient descent optimization and back propagation, regularization in neural networks, dropout. normalization methods.
• Introduction to deep learning - feedforward, convolutional and recurrent networks, practical considerations in deep learning.
• Introduction to graphical models - directed and undirected graphs, belief propagation.

Grading Details

Pre-requisites

• Must - Random Process/Probablity and Statistics
• Must - Linear Algebra/Matrix Theory

Textbooks

Slides