Course Synthesis and Bridge to SML
One map of the course¶
Matrices and images — data as linear objects
kNN and k-means — classification and clustering as first algorithms
Curse of dimensionality — why high dimension changes everything
SVD / PCA / low-rank — finding structure in matrices
Random graphs — structure of network data
Learning foundations — generalization without SVM/Bayes here
Deferred to other courses¶
| Topic | Where |
|---|---|
| Bayesian decision theory, Naive Bayes | Statistical Machine Learning |
| Gaussian mixtures / EM depth | Statistical Machine Learning |
| HMM | Statistical Machine Learning |
| MCMC, Metropolis–Hastings, Gibbs | Statistical Machine Learning |
| Graphical models, belief propagation | Statistical Machine Learning |
| SVM, kernels, nonlinear separators | Separate ML course |
Closing checklist¶
Student talks (ranking / voting / Small World / spectral clustering)
Review of key demos (curse, SVD compression, ER phase transition)
How to read BHK after this course