ARTIFICIAL INTELLIGENCE

&
MACHINE LEARNING

Prepared By
MOHAMMAD ASLAM
 Outline
Artificial Intelligence (AI)
Categories of AI
Applications of AI
Building AI system
Agents and Environments
Rational Agents
Environment
Machine learning
•
Supervised Learning
•
Unsupervised Learning
•
Semi-supervised Learning
•
Reinforced Learning

30/05/24 2
 Artificial Intelligence (AI)
•
Study of computer systems that attempt to model and apply the intelligence of the human mind
•
Deals with the simulation of intelligent behavior in computers
•
Capability of a machine to emulate human behavior

30/05/24 3
 Categories of AI
•
Game Playing
•
Speech Recognition
•
Computer Vision
•
Expert Systems
•
Mathematical Theorem Proving
•
Natural Language Understanding
•
Scheduling and Planning
•
Artificial Neural Networks
•
Machine Learning

30/05/24 4
 Applications of AI
1. Business; financial strategies
2. Engineering: check design, offer suggestions to create new product, expert
systems for engineering problems
3. Manufacturing: assembly, inspection and maintenance
4. Medicine: monitoring, diagnosing
5. Education: in teaching
6. Fraud detection
7. Object identification
8. Information retrieval
9. Space shuttle scheduling

30/05/24 5
 Building AI system
•
Perception
•
Reasoning
•
Action

30/05/24 6
 Agents and Environments

30/05/24 7
 Agents and Environments (contd.)
•
Agent: perceives its environment through sensors and acts on the environment through actuators
•
Percept: input perceived by agent at any given instance
•
Agent Function: maps any percept sequence to an action
•
Agent program: The agent program implements the agent function for the artificial agent

30/05/24 8
 Rational Agent
A rational agent will always take the action that will cause the agent to be most successful
The right action to be taken depends on 4 criteria
•
The performance measure defining the criterion of success
•
The agent’s prior knowledge of the environment
•
The actions that the agent can perform
•
The agent’s percept sequence up to now

30/05/24 9
 Omniscience ,Learning and Autonomy
•
An Omniscient agent knows the actual outcome of its actions and acts accordingly (impossible in
reality)
•
A rational agent that learns from its precept sequence is autonomous
•

30/05/24 10
 Environments
Environment is surrounding of the agent
Environment types
•
Accessible vs. inaccessible or Fully observable vs Partially Observable
•
Deterministic vs. Stochastic
•
Episodic vs. Non-Episodic
•
Static vs. Dynamic
•
Discrete vs. continuous

30/05/24 11
 Machine Learning
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>

30/05/24 12
 Machine Learning
Traditional Programming
Data
Computer Output
Program

Machine Learning
Data
Computer Program
Output

30/05/24 13
 Classification of Machine Learning
Supervised learning
Unsupervised learning
Reinforcement learning
Semi-supervised learning

30/05/24 14
 Supervised Learning
• For every example in the data there is always a predefined outcome
• Models the relations between a set of descriptive features and a target (Fits
data to a function)
• 2 groups of problems:
•
Classification: Predicts which class a given sample of data (sample of
descriptive features) is part of (discrete value).
•
Regression: Predicts continuous values.

30/05/24 15
 Supervised Learning

30/05/24 16
 Advantages of Supervised learning
•
With the help of supervised learning, the model can predict the output on the basis of prior
experiences.
•
In supervised learning, we can have an exact idea about the classes of objects.
•
Supervised learning model helps us to solve various real-world problems such as fraud detection,
spam filtering,etc.

30/05/24 17
 Disadvantages of supervised learning
•
Supervised learning models are not suitable for handling the complex tasks.
•
Supervised learning cannot predict the correct output if the test data is different from the training
dataset.
•
Training required lots of computation times.
•
In supervised learning, we need enough knowledge about the classes of object.

30/05/24 18
 Unsupervised Learning
•
Models are not supervised using training dataset
•
Models itself find the hidden patterns and insights from the given data

30/05/24 19
 Types of Unsupervised Learning
Clustering
•
Groups similar objects into clusters
•
Commonalities amongst objects found by cluster analysis
Association
•
Finds relationship between entities in large database
•
Determines the set of items that occur together in large dataset

30/05/24 20
 Unsupervised Learning
Advantages
•
Labelled input data is not needed
•
Unlabelled data is easily available
Disadvantages
•
Difficult to implement
•
Less accurate

30/05/24 21
 Semi-supervised Learning
Combines supervised and unsupervised learning
Unsupervised learning is used to group similar data
Supervised learning is used to label similar data in the groups detected by unsupervised learning
Applications
•
Speech Analysis
•
Internet Content Classification
•
Protein Sequence Classification

30/05/24 22
 Reinforcement Learning
•
Feedback-based Machine learning technique
•
The agent learns automatically using feedbacks without any labeled data
•
Decision making is sequential
•
The agent learns with the process of hit and trial
•
The environment is stochastic, and the agent needs to explore it to reach to get the maximum
positive rewards

30/05/24 23
 Reinforced Learning Model

30/05/24 24
 Applications of Reinforced Learning
•
Managing self-driving cars
•
Addressing the energy consumption problem
•
Traffic signal control
•
Healthcare
•
Robotics
•
Marketing
•
Gaming

30/05/24 25
 Conclusion
•
Artficial Intelligence and Machine Learning enables entities and process to become smart
•
AI/ML techniques are increasingly being applied to solve real-world problems by training agents
using large datasets
•
AI is set to play an even bigger role in out daily lives and has the potential to herald 4’th industrial
revolution

30/05/24 26
 References
•
Machine Learning by Tom M. Mitchell
•
Artificial Intelligence, Elaine Rich, Kevin Knight, Shivasankar B. Nair, The McGraw Hill publications,
Third Edition
•
Artificial Intelligence: Structures and Strategies for Complex Problem Solving, Pearson Education,
6th ed., 2009.
•
Introduction to Machine Learning, Second Edition, Ethem Alpaydın, the MIT Press, Cambridge,
Massachusetts, London, England.
•
Machine Learning , Tom M. Mitchell, McGraw-Hill Science,
•
Understanding Machine Learning:From Theory to Algorithms, c 2014 by ShaiShalev-Shwartz and
Shai Ben-David, Published 2014 by Cambridge University Press.

30/05/24 27