ARTIFICIAL INTELLIGENCE
DEPARTMENT OF COMPUTER SCIENCE AND
ENGINEERING
NIT JALANDHAR
Branches of Computer Science
Human Intelligence
What makes us Humans, intelligent?
Human Intelligence
•When we can give correct answers to people’s questions.
•When we solve a difficult problem or puzzle.
•When we can decide the correct action to be taken.
•When we learn something fast.
•When we are able to recognize many things and remember
their names.
•When we can use clues to guess an answer.
What defines Human Intelligence?
• Ability to observe, recognize and understand
• Ability to make ‘smart’ decisions and solve problems
• Ability to learn and increase knowledge
What defines Human Intelligence?
Any agent who can perform the above is called an Intelligent Agent.
Artificial Intelligence?
It is the ability to imitate humans (such as using language/speech,
vision/image recognition, making predictions, learning,
problem-solving, ability to move and manipulate objects on their own)
Approaches of Artificial Intelligence
4 Approaches of AI:
1) Think humanly
2) Act humanly
3) Think rationally
4) Act rationally
Need Of AI?
• To do tasks that humans want to avoid because of the risks involved
• To do things faster
• To do things that require more power
• To be more accurate
• To overcome human inefficiency
• To achieve consistency
• To have machines as companions
• To understand how humans function and have evolved
Foundations of Artificial Intelligence
The foundation provides the disciplines that contributed ideas,
viewpoints and techniques to AI.
• Philosophy
• Mathematics and Statistics
• Economics
• Neuroscience
• Psychology
• Computer Science and Engineering
• Linguistics
Foundations of Artificial Intelligence
1. Philosophy
Contribution: Logic, reasoning, awareness, ethics.
How it helps AI:
• Ideas of how knowledge can be represented.
• Development of formal logic systems.
• Discussions about machine consciousness and morality (AI ethics).
Example: Logic-based AI systems.
Foundations of Artificial Intelligence
2. Mathematics and Statistics
Contribution: Algorithms, probability, optimization, graph theory.
How it helps AI:
• Designing machine learning models.
• Handling uncertainty (Bayesian networks, probability).
• Mathematical foundations of neural networks.
Example: Linear regression, decision trees, backpropagation.
Foundations of Artificial Intelligence
3. Economics
Contribution: Decision-making, utility theory, game theory.
How it helps AI:
• Helps in designing agents that maximize expected reward.
• Multi-agent systems and competitive/cooperative behaviour.
Example: Rational agents, auctions, reinforcement learning.
Foundations of Artificial Intelligence
4. Neuroscience
Contribution: Understanding how the human brain works.
How it helps AI:
• Inspiration for neural networks and deep learning.
• Cognitive architectures.
Example: Artificial Neural Networks (ANNs), convolutional neural
networks (CNNs).
Foundations of Artificial Intelligence
5. Psychology
Contribution: Human learning, perception, behaviour modelling.
How it helps AI:
• Modelling how humans think and learn.
• Developing cognitive models in AI.
Example: Reinforcement learning inspired by behavioural psychology.
Foundations of Artificial Intelligence
6. Computer Science and Engineering
Contribution: Data structures, algorithms, programming, hardware.
How it helps AI:
• Building efficient and scalable AI systems.
• Providing platforms for training and deploying models.
Example: AI frameworks (TensorFlow, PyTorch), AI chips, robotics.
Foundations of Artificial Intelligence
7. Linguistics
Contribution: Study of language structure and meaning.
How it helps AI:
• Development of Natural Language Processing (NLP).
• Machine translation, speech recognition.
Example: Chatbots, language models (like ChatGPT), text-to-speech.
History of Artificial Intelligence
1. Ancient Times (Before 1900s)
• People imagined artificial beings (robots, talking statues) in
mythology and stories.
• Greek philosophers like Aristotle developed logic, which is the
foundation of AI reasoning.
• No real AI, but ideas of intelligent machines began here.
History of Artificial Intelligence
2. 1940s–1950s: Birth of AI Concepts
Years Events
1943 McCulloch & Pitts created the first model of an artificial
neuron.
1950 Alan Turing proposed the question: "Can machines think?"
and introduced the Turing Test.
1956 John McCarthy organized the Dartmouth Conference and
coined the term “Artificial Intelligence.”
History of Artificial Intelligence
3. 1956–1970: Early Excitement (Golden Age of AI)
Researchers were optimistic: they believed machines would soon
match human intelligence.
• Logic Theorist – solved math problems using logic.
• ELIZA – an early chatbot simulating a psychologist.
• SHRDLU – understood commands in a virtual world.
History of Artificial Intelligence
4. 1970s: First AI Winter
• AI failed to meet expectations.
• Computers were too slow, and real problems were too complex.
• Funding and interest decreased – this period is called the AI
Winter.
History of Artificial Intelligence
5. 1980s: Rise of Expert Systems
AI regained popularity due to Expert Systems (rule-based decision
programs).
• Example: MYCIN – a medical diagnosis system.
• Japan started the Fifth Generation Computer Project.
• AI tools like LISP became popular.
History of Artificial Intelligence
6. 1987–1993: Second AI Winter
• Expert systems became too expensive and failed to scale.
• Again, interest and funding declined.
History of Artificial Intelligence
7. 1990s–2000s: AI Revival (Machine Learning Era)
• Faster computers and more data led to Machine Learning.
• Major events:
• 1997: IBM's Deep Blue defeated chess champion Garry
Kasparov.
• 2002: First commercial robot vacuum (Roomba).
History of Artificial Intelligence
8. 2010–Present: AI Explosion (Deep Learning Era)
• Thanks to big data, powerful GPUs, and neural networks, AI grew
rapidly.
• 2011: IBM Watson won Jeopardy!
• 2012: AlexNet revolutionized image recognition.
• 2016: AlphaGo beat a human champion at the complex game
Go.
• 2020s: Tools like ChatGPT, self-driving cars, face recognition,
and AI in medicine became widespread.
History of Artificial Intelligence
9. The Future: General, Ethical & Explainable AI
• Goal: Build AGI (Artificial General Intelligence) – machines that
can do anything a human can.
• Focus is shifting to:
• Ethical AI (no bias or harm)
• Explainable AI (understandable decision-making)
• Human-AI collaboration
Basic Components of AI
AI’s basic Components = Learning + Reasoning +
Problem Solving + Perception + Language + Action
Basic Components of AI
1. Learning
The ability to improve performance from experience.
Types:
•Supervised learning – learns from labeled data.
•Unsupervised learning – finds patterns in unlabeled data.
•Reinforcement learning – learns through trial and error
with feedback.
Basic Components of AI
2. Reasoning
Drawing logical conclusions from known facts or rules.
Can be:
•Deductive – applying general rules to specific cases.
•Inductive – finding general rules from specific examples.
•Probabilistic – making decisions under uncertainty.
Basic Components of AI
3. Problem Solving
Finding solutions to specific tasks or challenges.
Approaches:
• Search algorithms (e.g., A*, DFS, BFS)
• Optimization methods (e.g., genetic algorithms, swarm
optimization)
Basic Components of AI
4. Perception
Understanding the environment using sensory input.
Examples:
• Computer vision – interpreting images/video.
• Speech recognition – converting spoken words into text.
Basic Components of AI
5. Natural Language Understanding & Generation
Interpreting and producing human language.
Includes:
• Chatbots
• Machine translation
• Summarization
• Sentiment analysis
Basic Components of AI
5. Action
Taking decisions or performing physical/digital actions based on AI’s
understanding.
Examples:
• Recommending a product
• Moving a robot arm
• Navigating a self-driving car
Branches of AI
