Selected topics in Computer Science

Selected topics in CS
School of Informatics Department of
Computer Science
By: Melaku Bayih

Topics to be cover
 Introduction
 Introduction to Artificial Intelligence(AI)
 Robotics
 Basic concepts of Machine Leaning (ML)
 Internet of things (IoT)
2

Introduction
 This course will address a variety of theoretical and/or technological
issues related to computer science and provides an opportunity for
students to undertake a term-long software development or research
project. Topics to be covered each term are decided by the instructor in
consultation with students. Students will work individually or in small
groups on projects related to these topics.
3

AI vs. ML
Artificial Intelligence is the broader concept of machines being able to carry out
tasks in a way that we would consider “smart”. And, Machine Learning is a
current application of AI based around the idea that we should really just be able
to give machines access to data and let them learn for themselves.
On a broad level, we can differentiate both AI and ML as: AI is a bigger concept
to create intelligent machines that can simulate human thinking capability and
behavior, whereas, machine learning is an application or subset of AI that allows
machines to learn from data without being programmed explicitly.
4

How is machine learning related to AI?
While machine learning is based on the idea that machines should be able to learn
and adapt through experience, AI refers to a broader idea where machines can
execute tasks "smartly." Artificial Intelligence applies machine learning, deep
learning and other techniques to solve actual problems.
It’s your time to innovate the future!
5

Session one
Artificial Intelligence and it’s
Application
6

What is Artificial intelligence (AI)
Artificial Intelligence is a term, which consists of two words.
Artificial
Artificial is something that is not real and which is kind
of ‘fake’ because it is simulated. The simplest thing what
I can think of which is artificial is artificial grass.
Like Artificial grass which is often used for sports,
because it is more resistant and therefore can be used
longer than real grass.
7

Intelligence
 Intelligence is very complex term. It can be defined in many
different ways like logic, understanding, self-awareness,
emotional knowledge, planning, creativity and of course problem
solving
 We call us, humans, intelligent, because we all do the above
mentioned things.
 We perceive our environment, learn from it and take action
based on what we discovered.
8
…cont.

…cont.
Artificial Intelligence is acted by machines, computers and mainly
software. Machines mimic, here we see why it is called artificial, some kind
of cognitive function based on environment, observations, rewards and
learning process.
9

Artificial intelligence (AI)
 The term AI was introduced by Prof. John McCarthy at a
conference at Dartmouth College in 1956.
 McCarthy defines AI as the “science and engineering of making
intelligent machines, especially intelligent computer programs”.
 You interact with AI systems daily but might not be aware of it.
 Every time that you use a search engine such as Google or Bing,
explore news websites such as the BBC or the New York Times,
talk to a virtual assistant such as Siri, or use an automated
language translation service, you are dealing with intelligent
systems.
10

 Generally, AI occupies a wide landscape and there are many potentials
uses for it. The objective of this chapter is to familiarize you with AI,
which increases its influence over our daily lives.
 Artificial Intelligence is a sub field of computer science that aims at
building computer systems that can perform tasks that normally
require human intelligence.
 For years, the challenging goal of AI has been developing computer
systems that equal or exceed human intelligence. AI-based machines
are intended to perceive their environment and take actions that
optimize their level of success.
11
…cont.

 AI research uses techniques from many fields, such as linguistics,
economics, and psychology.
 These techniques are used in applications, such as control systems,
natural language processing, facial recognition, speech recognition,
business analytics, pattern matching, and data mining
12
…cont.

Questions
1. What is Artificial Intelligence? Give an example of where AI is used on
a daily basis.
2. What is the difference between AI, Machine Learning and Deep
Learning?
3. List some application of AI?
4. What is an artificial intelligence Neural Networks?
5. What is Prolog in AI?
13

Session two
ROBOTICS AND IT’S TYPE
14

16
Robotics
Robotic History
Robotic
Technology
Types of
Robots

What is a Robot…?17
A re-programmable, multifunctional,
automatic industrial machine
designed to replace human in
hazardous work. It can be used as :-
•An automatic machine sweeper
•An automatic car for a child to play
with
•A machine removing mines in a war
field
•In space
•In military , and many more..

18
Roboticsisscienceof designingor building anapplication of robots. Simply ,Robotics
may be defines as “The Study of Robots”. The aim of robotics is to design an
efficient robot.
Robotics is needed because:-
•Speed
• Can work in hazardous/dangerous temperature
• Can do repetitive tasks
• Can do work with accuracy

20
The word robot was introduced to the public by Czech writer
Karel Capek(1890-1938) in his play R.U.R. (Rossum's Universal
Robots), published in 1920. The play begins in a factory that
makes artificial people called robots . Capek was reportedly
several times a candidate for the Nobel prize for his works .
The word "robotics", used to describe this field of
study, was coined accidentally by the Russian –
born ,American scientist and science fiction writer,
Isaac Asimov(1920-1992) in 1940s.

21
Asimov also proposed his three "Laws of Robotics", and he later
added a “zeroth law”.
Zeroth Law : A robot may not injure humanity, or, through in
action, allow humanity to come toharm
First Law : A robot may not injure a human being, or, through in action,

23
Sensors
Effectors
Actuators
Controllers
Arms

Robotic Types26
The most common types of Robots are…
Mobile Robots

27
Mobile robots are of two types….
Rolling robots have wheels to move around. They can
quickly and easily search.
However they are only useful in flat areas.
Robots on legs are usually brought in when the
terrain is rocky. Most robots have at least 4 legs;
usually they have 6 or more.

28
Robots are not only used to explore areas or imitate a
human being. Most robots perform repeating tasks without
ever moving an inch. Most robots are ‘working’ in industry
settings and are stationary.
Autonomous robots are self supporting or in other
words self contained. In a way they rely on their own
‘brains’.

29
A person can guide a robot by remote control.
A person can perform difficult and usually dangerous
tasks without being at the spot where the tasks are
performed.
Virtual robots don’t exits In real life. Virtual robots are
just programs, building blocks of software inside a
computer.

30
Going to far away planets.
Going far down into the unknown waters and mines where humans would
be crushed
Giving us information that humans can't get
Working at places 24/7 without any salary and food. Plus they don't
get bored
They can perform tasks faster than humans and much more
consistently and accurately
Most of them are automatic so they can go around by themselves without
any human interference.
 People can lose jobs in factories
 It needs a supply of power
It needs maintenance to keep it running .
It costs money to make or buy a robot

BMW Car Factory ROBOTS - Fast Manufacturing
31

1. What is robotics and list types ?
2. Define robotics technology ?
3. What is the advantages and disadvantages of robotics?
4. Why is robotics need?
5. What is laws of robotics?
32 Questions

Session three
MACHINE LEARNING AND IT’S
APPLICATIONS
33

What is Machine Learning?
 Machine Learning
 Study of algorithms that
 improve their performance
 at some task
 with experience
 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
34

Machine Learning definition
Arthur Samuel (1959).Machine Learning: Field of study that gives computers
the ability to learn without being explicitly programmed.
Tom Mitchell (1998) Well-posed Learning Problem: A computer program is
said to learn from experience E with respect to some task T and some
performance measure P, if its performance on T, as measured by P, improves
with experience E.
Suppose your email program watches which emails you do or do not mark as
spam, and based on that learns how to better filter spam. What is the task T in
this setting?
A branch of artificial intelligence, concerned with the design and development
of algorithms that allow computers to evolve behaviors based on empirical
data.
35

Growth of Machine Learning
 Machine learning is preferred approach to
 Speech recognition, Natural language processing
 Computer vision
 Medical outcomes analysis
 Robot control
 Computational biology
 This trend is accelerating
 Improved machine learning algorithms
 Improved data capture, networking, faster computers
 Software too complex to write by hand
 New sensors / IO devices
 Demand for self-customization to user, environment
 It turns out to be difficult to extract knowledge from human experts  failure of expert
systems in the 1980’s.
36

Applications
 Association Analysis
 Supervised Learning
 Classification
 Regression/Prediction
 Unsupervised Learning
 Reinforcement Learning
37

Learning Associations
 Basket analysis:
P (Y | X ) probability that somebody who buys X also buys Y where X and Y
are products/services.
Example: P ( chips | beer ) = 0.7
38
Market-Basket transactions
TID Items
1 Bread, Milk
2 Bread, Diaper, Beer, Eggs
3 Milk, Diaper, Beer, Coke
4 Bread, Milk, Diaper, Beer
5 Bread, Milk, Diaper, Coke
Itemset – A collection of one or more items
Example: {Milk, Bread, Diaper}
k-itemset An itemset that contains k items
Support count ( ) – Frequency of occurrence of an itemset –
E.g. ({Milk, Bread , Diaper}) = 2
Support – Fraction of transactions that contain an itemset ---
-------E.g. s({Milk, Bread, Diaper}) = 2/5

Classification39
 Example: Credit scoring
 Differentiating between low-
risk and high-risk customers
from their income and
savings
Discriminant: IF income > θ1 AND savings > θ2
THEN low-risk ELSE high-risk
Model

Classification: Applications
 Also known as Pattern recognition
 Face recognition: Pose, lighting, occlusion (glasses, beard), make-up,
hair style
 Character recognition: Different handwriting styles.
 Speech recognition: Temporal dependency.
 Use of a dictionary or the syntax of the language.
 Sensor fusion: Combine multiple modalities; eg, visual (lip image) and acoustic for
speech
 Medical diagnosis: From symptoms to illnesses
 Web Advertising: Predict if a user clicks on an ad on the Internet.
Classification is the task of learning a target function f that maps attribute
set x to one of the predefined class labels y.
40

General approach to classification
 Training set consists of records with known class labels
Training set is used to build a classification model.
A labeled test set of previously unseen data records is used to evaluate the
quality of the model.
The classification model is applied to new records with unknown class labels
41

Face Recognition
Training examples of a person
42

Prediction: Regression43
 Example: Price of a used car
 x : car attributes
y : price
y = g (x | θ )
g ( ) model,
θ parameters

Supervised Learning: Uses
Example: decision trees tools that create rules
 Prediction of future cases: Use the rule to predict the output for future
inputs
 Knowledge extraction: The rule is easy to understand
 Compression: The rule is simpler than the data it explains
 Outlier detection: Exceptions that are not covered by the rule, e.g., fraud
44

Unsupervised Learning
 Learning “what normally happens”
 No output
 Clustering: Grouping similar instances
 Other applications: Summarization, Association Analysis
 Example applications
 Customer segmentation in CRM
 Image compression: Color quantization
 Bioinformatics: Learning motifs
Finding groups of objects such that the objects in a group will be similar
(or related) to one another and different from (or unrelated to) the
objects in other groups known as clustering analysis.
45

Reinforcement Learning
 Topics:
 Policies: what actions should an agent take in a particular situation
 Utility estimation: how good is a state (used by policy)
 No supervised output but delayed reward
 Credit assignment problem (what was responsible for the outcome)
 Applications:
 Game playing
 Robot in a maze
 Multiple agents, partial observability, ...
46

 Reinforcement learning, the third popular type of machine learning, aims at
using observations gathered from the interaction with its environment to take
actions that would maximize the reward or minimize the risk.
47
…cont.

Questions
1. What is machine learnings?
2. Applications of ML?
3. What it mean supervised and unsupervised ml?
4. Explain classification and clustering?
5. what is Regression and Associations?
48

Session four
Internet Of Things And Smart
City
49

Internet of Things(IoT)50
What is IoT
Need for IoT
Applications of IoT
Future Scope

What is IoT51
 The Internet of Things is a platform where regular devices are connected to the
Internet, so they can interact, collaborate and exchange data with each other..

NEED FOR IoT
For all devices to:
Reducing human intervention into a machine cycle.
52
Interact Collaborate
Share
experiences

APPLICATIONS OF IoT53
IoT in Smart Cities
Innovative Solution to Traffic Congestion
Energy-efficient Buildings
Improved Public Safety

IoT in
Agriculture
Precision Farming
Smart Irrigation
Smart Greenhouse

IoT in
Industrial
Automation
Optimization and Time Saving
Quality Control and Inventory Mgmt.
Cost and Labor Efficient

APPLICATIONS OF IoT
56
Prediction
Response Recoverypreparedness
IoT in Disaster
Management

FUTURE SCOPE
 ENERGY: Energy efficient algorithms need to be designed for systems to be active
longer
 SECURITY We need information seclusion methods to secure data and privacy
 REAL TIME We need to reduce the gap between machine real-time and actual
real-time
57

58
In general, a smart city is a city that uses technology to provide services and solve city problems.
A smart city does things like improve transportation and accessibility, improve social services,
promote sustainability, and give its citizens a voice. Though the term “smart cities” is new, the
idea isn't.
The aim of smart cities is to: Use advanced technology, data and analytics to improve
management of city resources and lives of citizens.
Smart City

Features of Smart Cities
59 The core infrastructure elements in a smart city would include:
•adequate water supply,
•assured electricity supply,
•sanitation, including solid waste management,
•efficient urban mobility and public transport,
•affordable housing, especially for the poor,
•robust IT connectivity and digitalization,
•good governance, especially e-Governance and citizen
participation,
•sustainable environment,
•safety and security of citizens, particularly women,
children and the elderly, and
•health and education.

Smart city views
60

 Some typical features of comprehensive development in Smart Cities are
described below.
 Promoting mixed land use in area based developments–planning for
‘unplanned areas’ containing a range of compatible activities and land
uses close to one another in order to make land use more efficient. The
States will enable some flexibility in land use and building bye-laws to
adapt to change;
 Housing and inclusiveness – expand housing opportunities for all;
 Creating walkable localities –reduce congestion, air pollution and
resource depletion, boost local economy, promote interactions and
ensure security. The road network is created or refurbished not only for
vehicles and public transport, but also for pedestrians and cyclists, and
necessary administrative services are offered within walking or cycling
distance;
63

…Cont.
64
Preserving and developing open spaces – parks, playgrounds, and recreational
spaces in order to enhance the quality of life of citizens,
reduce the urban heat effects in Areas and generally promote eco-balance;
Promoting a variety of transport options – Transit Oriented Development
(TOD), public transport and last mile para-transport connectivity;
Making governance citizen-friendly and cost effective – increasingly rely on
online services to bring about accountability and transparency, especially using
mobiles to reduce cost of services and providing services without having to go to
municipal offices.

…cont.
Forming e-groups to listen to people and obtain feedback and use online monitoring of programs and
activities with the aid of cyber tour of worksites;
Giving an identity to the city – based on its main economic activity, such as local cuisine, health,
education, arts and craft, culture, sports goods, furniture, hosiery, textile, dairy, etc.; Applying Smart
Solutions to infrastructure and services in area-based development in order to make them better. For
example, making Areas less vulnerable to disasters, using fewer resources, and providing cheaper
services.
65

Questions
1. What is IoT?
2. List Applications of IoT ?
3. What is the need of IoT?
4. Explain IoT in Disaster Management?
5. List some features of Smart city?
66

67

Selected topics in Computer Science

Recommandé

Recommandé

Contenu connexe

Tendances

Tendances (20)

Similaire à Selected topics in Computer Science

Similaire à Selected topics in Computer Science (20)

Plus de Melaku Bayih Demessie

Plus de Melaku Bayih Demessie (10)

Dernier

Dernier (20)

Selected topics in Computer Science