Lecture No.

1.0

Introduction
Instructor:
Prof. Dr. M Sultan Zia
A Few Quotes
►“A breakthrough in machine learning would be worth
ten Microsofts” (Bill Gates, Chairman, Microsoft)
►“Machine learning is the next Internet”
(Tony Tether, Director, DARPA)
►Machine learning is the hot new thing”
(John Hennessy, President, Stanford)
►“Web rankings today are mostly a matter of machine learning”
(Prabhakar Raghavan, Dir. Research, Yahoo)
►“Machine learning is going to result in a real revolution” (Greg
Papadopoulos, CTO, Sun)
►“Machine learning is today’s discontinuity”
(JerryCOMSAT
S
Yang, CEO, Yahoo) 2
 Grading

15

50

30

Exams Projects Homework Participation

Projects
 Organization
 Self-defined topic related to your interests and research
 Groups of 2 students
 Deliverables
 Proposal (June 03)
 Poster Presentation (July 01)
 Code + Report V1 (July 15)
 Code + Report V2 (July 22)
 Peer review (July 29)
 Author rebuttal (Aug. 05)
 What Is Machine Learning?
►Automating automation
►Getting computers to program themselves
►Writing software is the bottleneck
Let the data do the work instead!

Traditional Data
Computer Output
Programming Program

Machine Data
Computer Program
Learning Output 5
COMSAT
S
Magic?

No, more like gardening

• Seeds = Algorithms
• Nutrients = Data
• Gardener = You
• Plants = Programs

6
COMSAT
S
Machine Learning
►Machine learning is a field of computer science that gives
computers the ability to learn without being explicitly
programmed.

►Machine learning is a discipline of artificial intelligence (AI)

that provides systems the ability to automatically learn and
improve from experience without being explicitly programmed.
Machine learning focuses on the development of computer
programs that can access data and use it to learn for themselves.

7
COMSAT
S
Machine Learning (Definition)

A computer program is said to learn

 from experience E
 with respect to some class of tasks T
 and performance measure P,

if its performance at tasks in T, as measured by P,

improves with experience E.
8
COMSAT
S
Applications

Almost Everywhere

9
COMSAT
S
 10
COMSAT
S
ML in a Nutshell
►Tens of thousands of machine learning
algorithms
►Hundreds new every year
►Every machine learning algorithm has three
components:
►Representation
►Evaluation
►Optimization

11
COMSAT
S
Representation
►Decision trees
►Sets of rules / Logic programs
►Instances
►Graphical models (Bayes/Markov nets)
►Neural networks
►Support vector machines
►Model ensembles
►CNNs
►Etc.
COMSAT
12
S
 ►Accuracy
►Precision and recall
►Squared error
►Likelihood
►Posterior probability
Evaluation ►Cost / Utility
►Margin
►Entropy
►K-L divergence
►Etc. 13
COMSAT
S
 ►Combinatorial optimization
►E.g.: Greedy search
►Convex optimization
►E.g.: Gradient descent
Optimization ►Constrained optimization
►E.g.: Linear programming
►Genetic Algorithms
►Etc.
14
COMSAT
S
Types of Learning
►Supervised (inductive) learning
►Training data includes desired outputs
►Unsupervised learning
►Training data does not include desired
outputs
►Semi-supervised learning
►Training data includes a few desired outputs
►Reinforcement learning
►Rewards from sequence of actions

15
COMSAT
S
ML in Practice
►Understanding domain, prior knowledge, and goals
►Data integration, selection, cleaning,
pre-processing, etc.
►Deciding & Building the Model
►Learning models
►Interpreting results
►Consolidating and deploying discovered knowledge
►Loop
16
COMSAT
S
??? ((( )))

17