|
CSC2515 Fall 2004 - Lectures
Tentative Lecture Schedule
- Sept 14 -- Machine Learning:
Introduction to Machine Learning, Generalization and Capacity
(notes [ps]
[pdf])
- Sept 21 --Classification 1:
KNN, linear discriminants, decision trees
(notes [ps]
[pdf])
- Sept 28 -- Classification 2:
probabilistic classifiers: class-conditional Gaussians,
naive Bayes, logistic regression, neural nets for classification
(notes [ps]
[pdf])
- Oct 5: Assignment 1 (Classification) posted
- Oct 5 -- Regression 1:
constant model, linear models, generalized additive models
(e.g. RBFs), locally weighted regression,
multilayer perceptrons/neural networks
(notes [ps]
[pdf])
- Oct 12 -- Objective Functions and Optimization:
error surfaces, weight space, gradient descent, stochastic gradient,
conjugate gradients, second order methods, convexity, enforcing constraints
(notes [ps]
[pdf])
- Oct19: Assignment 1 due at the start of class
- Oct 19 -- Regression 2 and Supervised Mixtures:
credit assignment problem, neural networks, radial basis networks,
kolmogorov's theorem,
backprop algorithm for efficiently computing gradients,
mixtures of experts, piecewise models
(notes [ps]
[pdf])
- Oct26: Assignment 2 (Regression) posted
- Oct 26 -- Unsupervised Learning 1:
Trees & Clustering
K-means, heirarchical clustering (alglomerative and divisive),
maximum likelihood trees, optimal tree structure
(notes [ps]
[pdf])
- Nov 2 -- Unsupervised Learning 2:
Mixture models and the EM Algorithm:
missing data, hidden variables,
Jensen's inequality, lower bound on marginal likelihood,
free energy interpretation, inference,
(notes [ps]
[pdf])
- Nov 9: Assignment 2 due
- November 9 -- Unsupervised Learning 3:
Continuous latent variable models, Factor Analysis, (Probabilistic)
PCA, Mixtures of Factor Analyzers, Independent Components Analysis
(notes [ps]
[pdf])
- Nov 16: Assignment 3 posted
- Nov 16 -- Time Series Models
autoregressive/Markov models, hidden Markov models
(notes [ps]
[pdf])
- Nov 23 -- 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 [ps]
[pdf])
- Nov 30: Assignment 3 due at the start of class
- Nov 30 -- Meta-Learning Methods:
stacking, bagging, boosting
(notes [ps]
[pdf])
- Dec 7 -- Kernel methods:
the kernel trick, support vector machines, kernel perceptrons,
sparsity, capacity control, dual problems
(notes [ps]
[pdf])
- December 20 -- projects due by email before 5pm
Send attachments or valid URL pointing to your report.
POSTSCRIPT or PDF only. DO NOT SUBMIT WORD, HTML OR OTHER FORMAT
FILES.
- December 20 -- all readings must be completed by 5pm.
email csc2515readings@cs
- Extra topics we may or may not 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
[
Home |
Course Information |
Lecture Schedule/Notes |
Textbook/Readings |
Assignments/Tests |
Computing |
]
CSC2515 - Machine Learning || www.cs.toronto.edu/~roweis/csc2515/
|