Statistical Machine Learning
(3-0-0-3)
CMPE Degree: This course is Not Applicable for the CMPE degree.
EE Degree: This course is Not Applicable for the EE degree.
Lab Hours: 0 supervised lab hours and 0 unsupervised lab hours.
Technical Interest Group(s) / Course Type(s): Digital Signal Processing
Course Coordinator:
Prerequisites: None.
Catalog Description
An introduction to the theory of statistical learning and practical machine learning algorithms with applications in signal processing and data analysis.Textbook(s)
The Elements of Statistical LearningCourse Outcomes
Not Applicable
Strategic Performance Indicators (SPIs)
Not Applicable
Topical Outline
1. Supervised learning
a) The Bayes classifier and the likelihood ratio test
b) Nearest neighbor classification
c) Linear classifiers
i. plugin classifiers (LDA, logistic regression, Naïve Bayes)
ii. the perceptron learning algorithm
iii. maximum margin principle and separating hyperplanes
d) Linear regression
i. least-squares linear regression
ii. the LASSO
e) Theory of generalization
i. overfitting
ii. concentration inequalities
iii. VC dimension and generalization bounds
iv. the bias-variance tradeoff
v. regularization
f) Nonlinear classifiers
i. nonlinear feature maps
ii. the kernel trick
iii. SVMs
iv. multi-layer neural networks
g) Nonlinear methods in regression
h) Error estimation and validation
2. Unsupervised learning
a) Linear dimensionality reduction and principal component analysis
b) Mutltidimensional scaling
c) Clustering
i. K-means
ii. GMMs and the EM algorithm
iii. spectral clustering
d) Density estimation
e) Feature selection
f) Nonlinear dimensionality reduction (manifold learning)
3. Other topics (as time permits)
a) Matrix factorizations
b) Graphical models
c) Ensemble methods (boosting, random forests)
d) - Deep learning