Transcript Lecture 1 , Jan - 14 - 2015

Machine Learning
Mehdi Ghayoumi
MSB rm 132
[email protected]
Ofc hr: Thur, 11-12 a
Machine Learning
Class & Sections
Class Lectures:
Section 1, Mon.,
11a-12:15p, HDN 109
Section 2, Wed.,
11a-12:15p, HDN 109
Machine Learning
What I expect from you:
•
Feedback and collaborate in class
•
Regular attendance
•
Hard work
•
Memorization of key concepts and Creativity
•
Self - learning
Machine Learning
My Goals:
• Give you some theoretical knowledge
• Publish our final approach as papers
• Promote our Smartness.
Machine Learning
Your Goals:
•
Your First Bonus.
Machine Learning
• Final:(1) 30%,
• Theory Assignments: (2)10%,
• Programming Assignments: (2)10%,
• Programming project: (1) 30%,
• Participation: ( All classes)10%,
• Quiz: (2) 10%,
A > 92%, A- > 85%,
B+ > 80%, B > 75%, B- > 70%,
C+> 65%, C > 60%, C- > 55%,
D+ > 53%, D > 50%
Machine Learning
• Final: 30%, Last week( Last session- Last week):
• Class slides and their examples,
• Class and home assignments,
• Class discussions.
Machine Learning
• Theory assignments: 2-10%:

Some Weeks homework assign, (Wednesdays),

No late homework accepted,

Written solutions must be your own,
Machine Learning
• Programming Assignments: 2- 10%:
Machine Learning
• Programming project: 30%,
•
First Report 5%
•
Second Report 5%
•
Project 20%
1.Team project only.
2. A list of topics will be provided.
3.The project work is collaborative.
Machine Learning
• Class Participation: 10%
Machine Learning
• Quiz: 2- 10%
Machine Learning
References:
"Pattern Recognition and Machine Learning", Christopher M. Bishop, Publisher:
Springer Verlag, ISBN: 978-0387-31073-2, 2006 (corrected edition, 2009).
Kevin Murphy, "Machine Learning - a Probabilistic Perspective", MIT Press, 2012.
(online via Kent Library)
Machine Learning
Send me these information:
1.
Level of your programming proficiency,
2.
Languages and databases that you know.
3.
Name of group members
Machine Learning
Machine Learning
Science is a systematic enterprise that builds and
organizes
knowledge
explanations
the universe.
and
in
the
predictions
form
about
of
testable
nature
and
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Why “Learn” ?
• Machine learning is programming computers to optimize a
performance criterion using example data or past experience.
• There is no need to “learn” to calculate payroll
• Learning is used when:
– Human expertise does not exist (navigating on Mars),
– Humans are unable to explain their expertise (speech
recognition)
– Solution changes in time (routing on a computer network)
– Solution needs to be adapted to particular cases (user
biometrics)
Machine Learning
What is Machine Learning?
• Optimize a performance criterion using example data or past
experience.
• Role of Statistics: Inference from a sample
• Role of Computer science: Efficient algorithms to
– Solve the optimization problem
– Representing and evaluating the model for inference
Machine Learning
• Apply a prediction function to a feature representation of
the image to get the desired output:
f(
f(
f(
) = “apple”
) = “tomato”
) = “cow”
Machine Learning
y = f(x)
Machine Learning
Training
Labels
Training
Images
Image
Features
Image
Features
Training
Learned
model
Learned
model
Prediction
Machine Learning
Machine Learning
Unsupervised
“Weakly” supervised
Fully supervised
Machine Learning
Machine Learning
Machine Learning
•
•
•
•
•
•
•
•
SVM
Neural networks
Naïve Bayes
Logistic regression
Decision Trees
K-nearest neighbor
RBMs
Etc.
Machine Learning
Resources: Journals
•
•
•
•
•
•
•
•
•
Journal of Machine Learning Research www.jmlr.org
Machine Learning
Neural Computation
Neural Networks
IEEE Transactions on Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence
Annals of Statistics
Journal of the American Statistical Association
...
Machine Learning
Resources: Conferences
•
International Conference on Machine Learning (ICML)
•
European Conference on Machine Learning (ECML)
•
Neural Information Processing Systems (NIPS)
•
Uncertainty in Artificial Intelligence (UAI)
•
Computational Learning Theory (COLT)
•
International Joint Conference on Artificial Intelligence (IJCAI)
•
•
International Conference on Neural Networks (Europe)
...
Thank you!