This outline is tentative and may change in the course of the semester.
- Structural Risk Minimization
- Loss Functions and Regularizers
- Beyond Gradient Descent: Newton’s Method and SGD
- Probability Estimation (MLE, MAP, and Bayesian parameter estimation)
- Performance Evaluation for ML
- Naive Bayes and Generative ML models
- Kernels
- Theory
- Kernel Machines (Kernel Regression, Kernel SVM)
- Gaussian Processes
- Regression
- Model Selection
- Neural Networks
- Deep Learning
- Autoencoders
- Convolutional NNs
- Unsupervised Learning I
- k-means Clustering
- GMMs and EM
- Unsupervised Learning II
- PCA and SVD for Dimensionality Reduction
- Latent Variable Models (PPCA)
- Semi-supervised Learning
- graph-based SSL
- SSL with SVMs
Optional Topics – time permitting:
- Graph-based Machine Learning
- Structured Data
- Graph Kernels
- Active Learning
- Sampling and Advanced Mixture Models
- MCMC / Gibbs sampling
- Dirichlet Processes, LDA for topic modeling
- Large-scale ML
- parallelizing ML algorithms
- large-scale linear algebra
- sparse GPs