Artificial Intelligence

Course Code: CS 451

Course Instructor: Dr. Umara Zahid
Recommended Books
1. Han, Jiawei, Micheline Kamber, and Jian Pei. Data Mining: Concepts
and Techniques, Third Edition. 3rd ed. Waltham, Mass.: Morgan
Kaufmann Publishers, 2012.
2. Machine Learning: A Probabilistic Perspective by Kevin P. Murphy
3. Pattern Recognition and Machine Learning by Christopher M.
Bishop
Course Objectives and Outcomes
Course Objectives
1. To develop skills of using recent machine learning software for solving practical problems.
2. To gain experience of doing independent study and research.
3. To introduce students to the basic concepts and techniques of Machine Learning.

Learning Outcomes
On completion of the course students will be expected to:
• Have a good understanding of the fundamental issues and challenges of machine learning: data,
model selection, model complexity, etc.
• Have an understanding of the strengths and weaknesses of many popular machine learning
approaches.
• Appreciate the underlying mathematical relationships within and across Machine Learning
algorithms and the paradigms of supervised and un-supervised learning.
• Be able to design and implement various machine learning algorithms in a range of real-world
applications.
Lecture Outline
• Machine Learning What and Why?
• Types of Machine Learning
• Supervised
• Unsupervised
• Reinforcement
• Applications of Machine Learning (Broad overview of the problems
and solutions)
• Difference between Data Science, Artificial Intelligence, Machine
Learning and Data mining
 Machine Learning What and Why?
We are drowning in information and starving for knowledge. — John
Naisbitt. (author and public speaker in the area of future studies)
Big Data
• Widespread use of personal computers and wireless communication leads
to “big data”
• We are both producers and consumers of data
• Data is not random, it has structure, e.g., customer behavior
• We need “big theory” to extract that structure from data for
(a) Understanding the process
(b) Making predictions for the future
Machine Learning Definition (Simple to Formal)
• Machine learning as a set of methods that can automatically detect patterns in
data, and then use the uncovered patterns to predict future data, or to perform
other kinds of decision making under uncertainty - Kevin P Murphy
• “Learning is any process by which a system improves performance from
experience.” - Herbert Simon
Definition by Tom Mitchell (1998):
• Machine Learning is the study of algorithms that
• improve their performance P
• at some task T
• with experience E.
A well-defined learning task is given by <P, T, E>.
 Machine Learning Vs. Traditional Programming
• Machine learning is programming computers to
optimize a performance criterion using example data Traditional Programming
or past experience. Data
Computer Output
• There is no need to “learn” to calculate payroll Program
• Learning is used when:
• Human expertise does not exist (navigating on Machine Learning
Mars), Data
• Humans are unable to explain their expertise Output
Computer Program
(speech recognition)
• Solution changes in time (routing on a computer
network)
• Solution needs to be adapted to particular cases
(user biometrics)
A Classic Example: It is very hard to say what
makes a “2”
Some more examples
Recognizing patterns:
• – Facial identities or facial expressions
• – Handwritten or spoken words
• – Medical images
Generating patterns:
• – Generating images or motion sequences
Recognizing anomalies:
• – Unusual credit card transactions
• – Unusual patterns of sensor readings in a nuclear power plant
Prediction:
• – Future stock prices or currency exchange rates
Defining the Learning Task
Improve on task T, with respect to
performance metric P, based on experience E
• T: Playing checkers
• P: Percentage of games won against an arbitrary opponent
• E: Playing practice games against itself
• T: Recognizing hand-written words
• P: Percentage of words correctly classified
• E: Database of human-labeled images of handwritten words
• T: Driving on four-lane highways using vision sensors
• P: Average distance traveled before a human-judged error
• E: A sequence of images and steering commands recorded while observing a human driver.
• T: Categorize email messages as spam or legitimate.
• P: Percentage of email messages correctly classified.
• E: Database of emails, some with human-given labels
State of the Art Applications
of AI/ML
Autonomous Cars

• Nevada made it legal for

autonomous cars to drive on roads
in June 2011
• As of 2013, four states (Nevada,
Florida, California, and Michigan)
have legalized autonomous cars
Autonomous Car Sensors
Face Recognition
Automatic Speech Recognition
Scene Labelling with Deep Learning
Types of Machine Learning
1. Supervised/ Predictive Learning
• Given: training data + desired outputs (labels)
2. Unsupervised/ Descriptive Learning
• Given: training data (without desired outputs)
3. Reinforcement Learning
• Works on the principle of feedback/ Rewards from sequence of actions
Supervised/ Predictive Learning
• In the predictive or supervised learning approach, the goal is to learn a
mapping from inputs x to outputs y, given a labeled set of input-output
pairs D = {(xi, yi)} where i =1 to N. Here D is called the training set, and N is
the number of training examples.
• Each training input xi is a D-dimensional vector of numbers, e.g. the height
and weight of a person. These are called features, attributes or covariates.
• Input xi could be a complex structured object, such as an image, a
sentence, an email message, a time series, a molecular shape, a graph, etc.
• The output or response variable can in principle be anything, but most
methods assume that yi is a categorical or nominal variable from some
finite set, yi ∈ {1, . . . , C} (such as male or female), or that yi is a real-valued
scalar (such as income level).
Classification Vs. Regression

When the output “yi” is categorical, the problem is known as

classification or pattern recognition, and when yi is real-valued, the
problem is known as regression.
Supervised Learning: Classification
• Binary Classification: y ∈ {0, 1}
• multiclass classification: more
than 2 classes
• Given (x1, y1), (x2, y2), ..., (xn,
yn)
• • Learn a function f(x) to predict
y given x
• – y is categorical ==
classification
Classification Examples
Supervised Learning: Regression
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y
given x
• – y is real-valued == regression
• Regression is just like classification
except the response variable is
continuous.
Regression Examples
1. Predict tomorrow’s stock market price given current market
conditions and other possible side information.
2. Predict the age of a viewer watching a given video on YouTube.
3. Predict the location in 3d space of a robot arm end effector, given
control signals (torques) sent to its various motors.
4. Predict the amount of prostate specific antigen (PSA) in the body as
a function of a number of different clinical measurements.
5. Predict the temperature at any location inside a building using
weather data, time, door sensors, etc.
Unsupervised Learning
• Given x1, x2, ..., xn (without
labels)
• Output hidden structure
behind the x’s
• E.g., clustering
Unsupervised Learning Examples
• Genomics application: group individuals by genetic similarity
Reinforcement Learning
• Given a sequence of states and actions with (delayed) rewards,
output a policy Policy is a mapping from state and actions that tells
you what to do in a given state
• Examples:
• – Credit assignment problem
• – Game playing
• – Robot in a maze
• – Balance a pole on your hand
The Agent-Environment Interface
Designing a Learning System (Simple)
• Define Objective
• Collect Data
• Prepare Data
• Select Algorithm
• Train Model
• Test Model
• Predict
• Deploy
Designing a Learning System (Formal)
• Choose the training experience
• Choose exactly what is to be learned
• i.e. the target function
• Choose how to represent the target
function
• Choose a learning algorithm to infer
the target
• function from the experience
Difference between Artificial Intelligence and
Machine Learning
Artificial intelligence Machine Learning

AI is the technology which enables a machine to ML is a subset of AI which allows a machine to

simulate human behavior. automatically learn from past data without
programming explicitly.

The goal of AI is to make a smart computer The goal of ML is to allow machines to learn
system like humans to solve complex problems. from data so that they can give accurate output.

In AI, we make intelligent systems to perform In ML, we teach machines with data to perform a
any task like a human. particular task and give an accurate result.

ML and Deep Learning are the two main subsets Deep Learning is a main subset of ML
of AI
AI is working to create an intelligent system ML is working to create machines that can
which can perform various complex tasks perform only specified tasks for which they are
trained.
Three Types of AI: Weak, general, and Strong Three types of ML: Unsupervised, Supervised,
Reinforcement
 Difference between Data Science and
Machine Learning
Data science is a concept used to
tackle big data and includes data
cleansing, preparation, and analysis. A
data scientist gathers data from
multiple sources and applies machine
learning, predictive analytics, and
sentiment analysis to extract critical
information from the collected data
sets. They understand data from a
business point of view and can provide
accurate predictions and insights that
can be used to power critical business
decisions