Ch1 Introduction

Content
1)History & overview of Artificial Intelligence
2) Definition of Artificial Intelligence
3) Artificial Narrow Intelligence, Artificial General
Intelligence , Artificial Super Intelligence
4) Concepts of Production, Agents and
Environments
5) Characteristic of Intelligent Agents, Concept of
Rationality, Nature of Environments.
 History and Overview of Artificial Intelligence (AI)
 Artificial Intelligence (AI) is a branch of computer
science that aims to create systems capable of
performing tasks that typically require human
intelligence.
 The concept of AI dates back to ancient times, with
myths of intelligent automatons, but its formal
exploration began in the mid-20th century.
 1950s: Alan Turing proposed the concept of a
"thinking machine" and developed the Turing Test as
a measure of intelligence.
 1956: The term "Artificial Intelligence" was coined
during the Dartmouth Conference, which marked the
beginning of AI as a formal discipline.
 1980s-1990s: Knowledge-based systems and expert
systems emerged, focusing on decision-making
using rules and facts.
 2000s-Present: Advances in machine learning,
neural networks, and deep learning have driven
rapid progress, enabling applications like self-driving
cars, natural language processing, and robotics.
Definition of Artificial Intelligence
 Artificial Intelligence can be defined as:
 Traditional Definition: The simulation of human
intelligence in machines that are programmed to
think, learn, and solve problems.
 Modern Definition: A multidisciplinary field that
focuses on creating systems capable of perceiving,
reasoning, learning, and adapting to achieve goals in
dynamic environments.
Types of Artificial Intelligence
 Artificial Narrow Intelligence (ANI):
 Specialized AI systems designed to perform
specific tasks efficiently.
 Examples: Virtual assistants (e.g., Siri,
Alexa), recommendation systems.
 Artificial General Intelligence (AGI):
 Hypothetical systems capable of performing
any intellectual task that a human can do.
  AGI remains a theoretical concept and is a
major goal of AI research.
 Artificial Super Intelligence (ASI):
 A stage where AI surpasses human
intelligence in all aspects.
 It poses potential benefits and risks, as it
could revolutionize industries or challenge
humanity’s control
Core Concepts in AI

 Production Systems:
 AI systems that use rules (productions) to
determine actions.
 Components:
 Rule Base: A set of condition-action rules.
 Working Memory: Facts stored during
problem-solving.
 Inference Engine: Executes rules to
solve problems.
 Agents and Environments:
 Agent: An entity capable of perceiving its
environment and taking actions to achieve
its goals.
 Environment: The external world with which
an agent interacts.
Characteristics of Intelligent Agents
 Intelligent agents possess the following
characteristics:
 Autonomy: Ability to operate without human
intervention.
 Reactivity: Responding to changes in the
environment.
 Proactiveness: Goal-driven behaviour to
achieve objectives.
 Adaptability: Learning and improving over
time.
 Concept of Rationality
 Rationality refers to making decisions that
maximize the agent’s performance measure
based on the information available.
 A rational agent selects actions that are most
likely to achieve its goals efficiently and
effectively
 Nature of Environments
 Environments are categorized based on their
characteristics:
 Fully Observable vs. Partially Observable:
 Fully observable: The agent has access to
all relevant information (e.g., chess).
 Partially observable: Information is limited
or incomplete (e.g., poker).
 Deterministic vs. Stochastic:
 Deterministic: The next state is completely
predictable from the current state and
action (e.g., tic-tac-toe).
  Stochastic: Outcomes involve randomness
(e.g., weather prediction).
 Static vs. Dynamic:
 Static: The environment does not change
during the agent's operation.
 Dynamic: The environment evolves over
time.
 Discrete vs. Continuous:
 Discrete: Limited, countable states and
actions (e.g., board games).
 Continuous: Infinite states and actions (e.g.,
robotic navigation).
 Core Components of AI
 Artificial Intelligence (AI) is built upon several
key components that work together to enable
machines to perform tasks that typically
require human intelligence.
 These components include algorithms, data,
computing power, and models.
 1. Algorithms
 Definition
 Algorithms are step-by-step procedures or
formulas for solving problems. In AI,
algorithms process data, make decisions, and
 Core Components of AI
 Artificial Intelligence (AI) is built upon several
key components that work together to enable
machines to perform tasks that typically
require human intelligence.
 These components include algorithms, data,
computing power, and models.
Algorithms
 Definition
 Algorithms are step-by-step procedures or
formulas for solving problems. In AI,
algorithms process data, make decisions, and
learn from patterns.
 Types of Algorithms
 Supervised Learning Algorithms: These
algorithms learn from labeled data and make
predictions based on that data. Examples
include linear regression, decision trees, and
support vector machines.
 Unsupervised Learning Algorithms: These
algorithms find hidden patterns or intrinsic
structures in input data that are not labeled.
Examples include k-means clustering and
principal component analysis (PCA).
 Reinforcement Learning Algorithms: These
algorithms learn by interacting with an
environment and receiving rewards or penalties.
They are used in applications like game playing
and robotic control.
2. Data
 Importance of Data
 Data is the foundation of AI. AI systems
require large amounts of data to learn and
make accurate predictions. The quality and
quantity of data significantly impact the
performance of AI models.
Types of Data
 Structured Data:
Databases and spreadsheets are organized
in a tabular format. Examples include
customer information, transaction records,
and sensor readings.
 Unstructured Data
Data that is not organized in a predefined
manner, such as text, images, audio, and
video. Examples include social media posts,
emails, and medical images.
 Data Processing:
Data often needs to be pre-processed before it is
fed into AI models. Data pre-processing includes
cleaning, normalizing, and transforming data to
ensure it is in the right format and quality for
analysis.
3. Computing Power
Role of Computing Power
Computing power is crucial for training and
deploying AI models. The complexity and size
of modern AI models require significant
computational resources to process large
datasets and perform complex calculations.
Types of Computing Resources
Central Processing Units (CPUs): General-
purpose processors that handle various
computing tasks. While essential, they are
often not sufficient for high-performance AI
tasks.
Graphics Processing Units (GPUs): Specialized
processors designed for parallel processing are
ideal for training deep learning models. GPUs
can efficiently handle the massive computations
required for training neural networks.
Tensor Processing Units (TPUs): Custom-
designed processors by Google specifically for AI
tasks, offering optimized performance for training
and inference of machine learning models.
4. Models
Definition
 AI models are mathematical representations
of real-world processes created by training
algorithms on data. These models can make
predictions, recognize patterns, and make
decisions based on new input data.
 Types of Models
 Machine Learning Models
 Deep Learning Models
 Ensemble Models
Application of AI
Thank you