CAP 6610, Machine Learning, Fall 2018
Place:CSE Building; E222
Time:MWF 4 (10:40-11:30 a.m.)
Instructor:
Arunava Banerjee
Office: CSE E336.
E-mail: arunava@cise.ufl.edu.
Phone: 505-1556.
Office hours: Wednesday 2:00 p.m.-4:00 p.m.
TA:
XXX XXXX
Office: CSE Exxx.
E-mail: xxx@cise.ufl.edu.
Office hours: Monday x:00 p.m.-x:00 p.m.(at CSE E309) or by appointment.
Pre-requisites:
- The official pre-requisites for this course is COT5615 (Mathematics for
Intelligent Systems). Specifically, knowledge of calculus and linear algebra
is necessary since we shall be touching on mathematical probability theory.
In addition, proficiency in some programming language is a must.
Textbook (recommended): Machine Learning: A Probabilistic Perspective,
Murphy, ISBN-10: 0262018020.
Reference: Pattern Recognition and Machine Learning,
Bishop, ISBN 0-38-731073-8.
Reference: Pattern Classification, 2nd Edition, Duda, Hart
and Stork, John Wiley, ISBN 0-471-05669-3.
Tentative list of Topics to be covered
- Review of mathematical probability theory; finite sample probability
bounds.
- Decision Trees
- Bayes decision theory
- Bayesian learning
- Maximum likelihood estimation and Expectation Maximization
- Linear and generalized linear models for regression and classification,
- Sparsity promoting priors with conjugates and their relationship to regularization
- Kernel methods including Support Vector Machines
- Error Back-propagation and Neural Networks
- Mixture models
- Hidden Markov models
- Principal Components Analysis
- Independent Components Analysis
- Reinforcement Learning
- Performance evaluation: re-substitution, cross-validation, bagging, and boosting
The above list is tentative at this juncture and the set of topics we end up
covering might change due to class interest and/or time constraints.
Please return to this page at least once a week to check
updates in the table below
Evaluation:
- One individual project spanning the semester: 10%
- Homework assignments (written and programming): 30%
- Two midterm exam: 30% each (2 hrs, in-class)
- There will be no makeup exams (Exceptions shall be made for those that
present appropriate letters from the Dean of Students Office).
The final grade will be on the curve.
Course Policies:
- Late assignments: All homework assignments are due before class.
- Plagiarism: You are expected to submit your own solutions to the
assignments. While the final project and presentation will be done in groups,
each member will be required to demonstrate his/her contribution to the work.
- Attendance: Their is no official attendance requirement. If you
find better use of the time spent sitting thru lectures, please feel free to
devote such to any occupation of your liking. However, keep in mind that it is
your responsibility to stay abreast of the material presented in class.
- Cell Phones: Absolutely no phone calls during class. Please turn
off the ringer on your cell phone before coming to class.
Academic Dishonesty:
See http://www.dso.ufl.edu/judicial/honestybrochure.htm
for Academic Honesty Guidelines. All academic dishonesty cases will be
handled through the University of Florida Honor Court procedures as
documented by the office of Student Services, P202 Peabody Hall. You may
contact them at 392-1261 for a "Student Judicial Process: Guide for Students"
pamphlet.
Students with Disabilities: Students requesting classroom
accommodation must first register with the Dean of Students Office. The Dean of
Students Office will provide documentation to the student who must then provide
this documentation to the Instructor when requesting accommodation.
Announcements
The second midterm on Dec 5th is NOT cumulative. You
will be tested on material covered after Neural networks.
As discussed in class, the final project report (written
in the form of a technical conference/journal paper) is due On or BEFORE
December 9th midnight.
Midterm 1 will be held on October 12th.
Midterm 2 will be held on the last day of classes, December 5th.
HW1 has been posted on Canvas. Please pay speacial
attention to deadline and how much space you have for each answer.
I have posted Durrett's book below. You are expected to
be comfortable with Chapter 1.
HomeWorks
HomeWork |
Due Date |
Solutions |
List of Topics covered
Week |
Topic |
Additional Reading |
Aug 19 - Aug 25 |
- Putative framework:
- Supervised, Unsupervised Learning. Reinforcement Learning
- Labeled/unlabeled datasets, training/testing.
- Generalization, over-fitting to training data
|
|
Aug 26 - Sep 01 |
- Continued with discussing roadmap for the rest of the semester.
- High level view of topics that we hope to cover
- why we need to know basic mathematical probability theory
|
|
Sep 02 - Sep 08 |
- Sample space, outcome
- Measurable space, sigma algebra
- limit supremum and limit infimum
- probability, random variable
- distribution function, density
|
|
Sep 09 - Sep 15 |
-
The "Risk functional" approach
Loss function, Hypothesis space
Empirical Risk and the Empirical risk minimization principle
- Application to classification, regression, density estimation
- Jensen's inequality
|
|
Sep 16 - Sep 22 |
- Decision Trees
- Impurity: Entropy, Gini, Misclasification
- NP-hardness of the problem
- Prunning, cross validation
|
|
Sep 23 - Sep 29 |
- Multivariate Regression
- Closed form solution
- Overdetermined, Underdetermined linear systems
- Moore-Penrose Pseudo inverse
|
|
Sep 30 - Oct 06 |
- Perceptron Learning rule
- Started mistake bound theorem for perceptron
- Energy function for perceptron learning and gradient descent
|
Here Perceptron convergence theorem
|
Oct 07 - Oct 13 |
- Artificial sigmoidal neuron and gradient descent on error
- Multi-layer perceptrons and Error back propagation
- Midterm
|
|
Oct 14 - Oct 20 |
- convolution neural networks, recurrent neural networks
- ReLU, Softmax, Dropout
- LSTM, ResNet, HighwayNet, DenseNet
- Background for Support vector machines
- Constrained optimization problem
- Convexity, Convex sets, local minima=global minima
|
LSTM A very good blog post that describes the idea
|
Oct 21 - Oct 27 |
- Lagrange multipliers
- Lagrange duality
|
|
Oct 28 - Nov 03 |
- Support vector machines
- maximum margin
- Primal and dual formulations
- The kernel trick; polynomial, gaussian kernels
|
|
Nov 04 - Nov 10 |
- Unsupervised learning
- Principal Component Analysis
- Derivation of Markov, Chebyshev, Hoeffding inequalities
|
|
Nov 11 - Nov 17 |
- Overview of Statistical learning theory
- Vapnik-Chervonenkis dimension
- Empirical Radamacher Complexity
- Maximum Likelihood
|
- VC Bound A very good informal description of the theory
|
Nov 18 - Nov 24 |
- Maximum Likelihood estimates of mean and variance for the
multi-variate Normal distribution.
- Thanksgiving
|
- VC Bound A very good informal description of the theory
|
Nov 25 - Dec 01 |
- K-Means clustering; objective function and algorithm
- Mixture of Gaussians and Expectation Maximization.
|
- Wiki on
K-Means clustering.
- Here are D'Souza's notes.
|