2. What is Intelligence?
Intelligence: Artificial Intelligence
-- “the capacity to learn and solve problems” (Websters dictionary)
----- in particular,
1. the ability to solve novel problems
2. the ability to act rationally
3. the ability to act like humans
Artificial Intelligence
build and understand intelligent entities or agents
2 main approaches: “engineering” versus “cognitive modeling”
3. What is Artificial Intelligence?
It is the science and engineering of making intelligent machines, especially
intelligent computer programs.
It is related to the similar task of using computers to understand human
intelligence, but AI does not have to confine itself to methods that are
biologically observable.
4. What’s involved in Intelligence?
Ability to interact with the real world
to perceive, understand, and act
e.g., speech recognition and understanding and synthesis
e.g., image understanding
e.g., ability to take actions, have an effect
Reasoning and Planning
modeling the external world, given input
solving new problems, planning, and making decisions
ability to deal with unexpected problems, uncertainties
Learning and Adaptation
we are continuously learning and adapting
our internal models are always being “updated”
e.g., a baby learning to categorize and recognize animals
5. What is Production System ?
A production system (or production rule system) is a computer program
typically used to provide some form of artificial intelligence, which consists
primarily of a set of rules about behavior.
These rules, termed productions, are a basic representation found useful in
automated planning, expert systems and action selection.
A production system provides the mechanism necessary to execute
productions in order to achieve some goal for the system.
6. Components of Production System.
A set of rules. Rule consist of LHS (Condition) & RHS (Action).
One or more knowledge databases.
A control strategy
A rule applier
7. Characteristics of Production System
Separation of Knowledge (the Rules) and Control (Recognize-Act Cycle)
Natural Mapping onto State Space Search (Data or Goal Driven)
Modularity of Production Rules (Rules represent chunks of knowledge)
Pattern-Directed Control (More flexible than algorithmic control)
Opportunities for Heuristic Control can be built into the rules
Tracing and Explanation (Simple control, informative rules)
Language Independence
Model for Human Problem Solving (SOAR, ACT*)
8. Types of Production System
A monotonic production system
A non monotonic production system
A partially commutative production system
A commutative production system.
9. Definitions of AI
The theory and development of computer systems able to perform tasks normally
requiring human intelligence, such as
• Visual perception,
• Speech recognition,
• Decision-making, and
• Translation between languages.
Refers to the simulation of human intelligence in machines that are programmed
to think like humans and mimic their actions. The term may also be applied to any
machine that exhibits traits associated with a human mind such as learning and
problem-solving.
The modern definition of AI is "the study and design of intelligent agents" where
an intelligent agent is a system that perceives its environment and takes actions
which maximizes its chances of success.
10. The Trend of AI
• Expert System for Industrial Applications using LISP, PROLOG, was on the rise
in 1980’s
• A comeback for Neural Networks in late 1980’s
• A steep fall for Expert system in early 1990’s
• A hibernation period for AI, since late 1990’s
• AI has returned with a BANG!!!!
11. EVOLUTION OF ARTIFICIAL INTELLIGENCE
11
1950s–1970s
Neural Networks
1980s–2010s
Machine Learning
Present Day
Deep Learning
Early work with neural networks stirs
excitement for “thinking machines.” Machine learning becomes popular.
Deep learning breakthroughs
drive AI boom.
12. Why AI?
One of Fastest Growing & cutting-edge Technologies
Has redefined the art of Computing for Problem Solving
Has brought-in a Paradigm Shift in Computing
Offers a spectrum of Computing Models for Problem Solving
Capable of handling ‘big data’
Seldom needs human intervention
AI is ideally suitable for Interdisciplinary Problems!!!
13. Arena of AI
Synonyms of AI are:
• computational intelligence, synthetic
intelligence or computational rationality.
AI research is an amalgamation of
• Computer science , Psychology , Philosophy ,
Neuroscience , Cognitive science,
Linguistics, Operations Research , Economics,
Control Theory ,Probability and Statistics ,
Optimization & Logic.
14. AI and Problem-Solving
No humans are required
Artificial Intelligence algorithms can provide Optimal and accurate solutions
AI is seamlessly contributing to transformation of society & industrial
revolution
Example:
Tea cup
Face
Phone
15. AI - The Context
Problems which can be handled by deterministic algorithm
e.g. Recognizing a 3D object from a given Scene, Handwriting
Recognition, Speech Recognition
Problems which don’t have a fixed solution and goal-posts keep changing.
System adapts and learns from experience
e.g. SPAM emails, Financial fraud, IT Security Framework
Where Solutions are Individual-Specific or Time-Dependent or Event-specific
e.g. Recommender System / Targeted Advertisements
For prediction, based on past and existing patterns
e.g. Prediction of Share Prices etc.,
16. AI and Beyond
General Artificial Intelligence (GAI): (Strong AI or true AI), refers to AI with advanced human-like
intelligence levels. While current machines are superior to humans at select tasks, there is
currently no AI that can successfully replicate the full depth and breadth of human skills and
cognition. This is a complement of Narrow AI.
Conversational AI: A popular NLP use is Conversational AI, commonly seen in online chatbots,
which use AI to mimic human conversation, via online chat. The chatbot market has taken off in
the past few years, bringing cost savings and improved customer service to nearly all industries,
especially in the booming e-commerce trend.
Machine Learning: Machine learning is an artificial intelligence-based technique that learns and
evolves based on experience through training. Some common machine learning applications include
operating self-driving cars, managing investment funds, performing legal discovery, making
medical diagnoses, and evaluating creative work. Some machines are even being taught to play
games.
17. Neural Networks: Neural networks is an artificial intelligence technique
modeled after connections in the human brain, capable of learning and
improving over time. Apple adapted Siri’s voice recognition technology to use
neural networks in 2014, and Google introduced the technology to improve
Chinese-English translations on Google Translate and many more.
Deep Learning: Deep learning or “unsupervised learning” is the next
generation of artificial intelligence that lets computers teach themselves.
Deep learning techniques program machines to perform high-level thought
and abstractions, such as image recognition. The technology has
advanced marketing by enabling more personalization, audience clustering,
predictive marketing, and sophisticated brand sentiment analysis.