CSC2515 Fall 2002 - Lectures

Tentative Lecture Schedule

• Sept 11
  Lecture 1: Introduction to Machine Learning, Generalization and Capacity (notes)

• Sept 18 --Classification 1:
  KNN, linear discriminants, decision trees (notes)

• Sept 25 -- Classification 2:
  naive Bayes, logistic regression, neural nets for classification (notes)

• Sept. 30: Assignment 1 (Classification) posted

• Oct 2 -- Regression 1:
  constant model, linear models, generalized additive models (e.g. RBFs), locally weighted regression, multilayer perceptrons/neural networks (notes)

• Oct 9 -- Regression 2 and Basic Optimization:
  error surfaces, weight space, credit assignment problem, neural networks, kolmogorov's theorem, backprop algorithm for efficiently computing gradients, gradient descent, stochastic gradient, (notes)

• October 15: Assignment 2 (Regression) handed out

• October 16: Assignment 1 due at the start of class

• Oct 16 -- Supervised Mixtures and Advanced Optimization:
  conjugate gradient, bound optimization , convexity, enforcing constraints mixtures of experts, piecewise linear models (notes)

• Oct 23 -- Unsupervised Learning 1: Mixture models and the EM Algorithm:
  missing data, hidden variables, Jensen's inequality, lower bound on marginal likelihood, free energy interpretation, inference, (notes)

• Oct30 -- Unsupervised Learning 2: Trees & Clustering
  K-means, heirarchical clustering, soft competitive learning (Mixtures of Gaussians), maximum likelihood trees, optimal tree structure (notes)

• November 6: Assignment 2 due

• November 6: Assignment 3 posted

• November 6 -- Unsupervised Learning 3:
  Continuous latent variable models, Factor Analysis, (Probabilistic) PCA, Mixtures of Factor Analyzers, Independent Components Analysis (notes)

• Nov 13 -- Time Series Models
  autoregressive/Markov models, hidden Markov models (notes)

• Nov 20: Assignment 3 due at the start of class

• Nov 20 -- Capacity Control:
  generalization and overfitting, No free lunch theorems, high dimensional issues.
  capacity control methods: weight decay, early stopping, cross validation, model averaging, intro to Bayesianism (notes)

• Nov 27 -- Meta-Learning Methods:
  stacking, bagging, boosting (notes)

• Dec 4 -- Kernel methods:
  the kernel trick, support vector machines, kernel perceptrons, sparsity, capacity control, dual problems (notes)

• Dec 18 -- projects due

• Extra topics we didn't have time for
  • other kernel machines: gaussian processes
  • linear dynamical systems, Kalman filtering
  • Approximate inference and learning:
    sampling, variational approximations, loopy belief propagation
  • Spectral Methods:
    Isomap,LLE, spectral clustering,
  • MaxEnt models:
    maximum entropy/energy-based models, iterative scaling, products of experts, dependency nets,
  • Matrix Factorizations:
    aspect models/LDA/plaids, non-negative matrix factorization
  • Automatic Structure Learning:
    sparsity priors, empirical Bayes, automatic relevance determination (MLII), structural EM

CSC2515 - Machine Learning || www.cs.toronto.edu/~roweis/csc2515/