 | |
|---|---|
| |
| |
| |
| |
 |  |
 | |
Introduction to Machine Learning and Pattern Recognition: Schedule
[ Course Homepage | Schedule and Course Material | Mailing List ]
|
|
|
||||||||||||||||||||||||||||||
|
This page contains the schedule, slide from the lectures, lecture notes, reading lists, assigments, and web links. I urge you to download the DjVu viewer and view the DjVu version of the documents below. They display faster, are higher quality, and have generally smaller file sizes than the PS and PDF.
Subjects treated: Intro, types of learning, nearest neighbor, how biology does it, linear classifier, perceptron learning procedure, linear regression,
IMPORTANT NOTE: This session will start in the usual classroom WWH-102, but the second part will be in room WWH-512 (Sun computer lab on the 5-th floor). Subjects treated: An introduction to the Lush programming language. Implementing the perceptron learning algorithm. The instructor for this lab seesion will be Fu-Jie Huang (Jie). You should all have a login on the Sun machines in the lab. If you have laptop, you are welcome to install Lush on it and to use it for the computer lab sessions instead of the labs's Sun workstations. Lush runs on Linux, Mac OS-X, Solaris, and on Windows under Cygwin. Click here to get the files for the lab and the homework.
HOMEWORK 01b:
Lush Tutorial: read the short tutorial on Lush at
the Lush documentation page.
Subjects treated: Intro, perceptron convergence theorem,
multivariate calculus refresher, loss functions, linear regression, LMS/Adaline.
Subjects treated: Energy-Based Models, Inference,
Loss Functions, Logistic Regression.
IMPORTANT NOTE:
Location to be announced.
.
Subjects treated: LAB: perceptron, LMS, Logistic Regression.
HOMEWORK 02a: Click here to get the files
for the lab and the homework.
To uncompress the homework file on Unix/Linux do
"tar xvfz lab-02a.tgz". This will create a directory
named "lab-02a". On Windows, use Winzip.
Subjects treated:
Learning and Generalization, Regularization.
Subjects treated: Multilayer and Multi-Module Systems,
Gradient Back-Propagation.
HOMEWORK 05b: computing Jacobians. Click one these links
to get the text of the homework: [DjVu | PDF | PS]
Subjects treated: Modules and Architectures.
Subjects treated: Special Architectures for
Time Series, Images, Audio, Video.
HOMEWORK 09a: speech recognition with
backpropagation and multilayer nets.
Click here to get the text
of the homework (caution: the file is 11MB).
Subjects treated: Convolutional Networks for
speech and image classification.
Slides: object recognition [DjVu].
Face detection, and other applications
Slides: face detection [DjVu].
Required Reading:
Gradient-based Learning Applied to Document Recognition by LeCun,
Bottou, Bengio, and Haffner; pages 1 to the first column of page 18:
[DjVu | .ps.gz ]
Subjects treated: distributions, marginalization, joint,
conditional, exponential family, Gaussians.
Subjects treated: density estimation. Maximum likelihood
estimation, Gaussian estimation, Parzen Windows.
Subjects treated: principal component analysis
HOMEWORK 10b: Principal Component Analysis
Click here to get the text
of the homework
Subjects treated: K-Means clustering, vector quantization,
image compression.
HOMEWORK 11a: K-Means Clustering
Click here to get the text
of the homework
Subjects treated: Ensemble methods,
Jackknife, Bagging, Boosting.
Support Vector Machines and Kernel Methods
Subjects treated: latent variables,
Expectation-Maximization algorithm (EM), mixtures of Gaussians.
HOMEWORK 12a: Mixture of Gaussians
Click here to get the text of the homework
Subjects treated: Training a handwritten digit recognizer.
FINAL PROJECT: most of the proposed topics of final projects
will be related to this lab session. You can make a proposal for a
different subject outside of the proposed list if you want. Proposed
subjects will include various ways of training various architectures
on the MNIST dataset of handwritten digits. Students will have 15
minutes to present the results of their project to the class in an
oral exam session on Thursday, May 5 from 4:00 PM to 5:30 PM. You can
do the project by yourself or in groups of two.
Subjects treated: Optimization, Hessian,
Convergence of gradient descent, Newton's algorithm,
Levenberg-Marquardt, Conjugate Gradient.
Required reading: "Efficient Backprop"
[DjVu]
[PS.GZ]
[PDF]
Subjects treated: Bayesian Learning Methods.
Subjects treated: Distributions on strings,
weighted finite-state machines, finite-state transducers.
Slides: Tutorial by Mehryar Mohri and Michael Riley: [DjVu | PDF | PS]
Subjects treated: Graphical models, factorized probability
distributions, belief propagation and the sum-product algorithm.
Subjects treated: Graphs Transformer Networks, sequence
labeling, discriminative training.
Required Reading:
Gradient-based Learning Applied to Document Recognition by LeCun,
Bottou, Bengio, and Haffner; pages 18 (sectionC) to 40.
[DjVu | .ps.gz ]
Applications of Machine Learning.
Review, Open Questions
Project Presentations.
Project Presentations.
|
|
||||||||||||||||||||||||||||||
|
|
|