BIT4202:ARTIFICIAL

INTELLIGENCE UNIT OUTLINE

• Introduction to AI
• AI in business
• Problem solving, search and control strategies
• Knowledge representation: issues
• Knowledge representation using predicate logic
• Knowledge representation using Rules
• Reasoning systems
• Learning systems: Machine learning
• Expert systems
• Natural Language processing
INTRODUCTION TO AI
• Chapter Objectives
• By the end of this chapter the learner should be able to;
• Define Artificial Intelligence (AI).
• Explain the Goals of AI,
• Describe the AI Approaches
• Explain AI Techniques
• Describe the Branches of AI
• Explain the Applications of AI.
DEFINITION OF ARTIFICIAL
INTELLIGENCE
• According to McCarthy (1956), Artificial Intelligence is the science and
engineering of making intelligent machines, especially intelligent
computer programs
• Artificial intelligence is the simulation of human intelligence processes
by machines, especially computer systems
 SUBSETS/branches OF AI
.
Definition of terms
• Intelligence: Intelligence relates to tasks involving mental processes,
e.g: Creating, solving problems, pattern recognition, classification,
learning etc.
• Intelligent behavior: intelligent behavior is the ability to achieve
human-level performance in all cognitive tasks, sufficient to fool an
interrogator
 Types of AI
• Artificial Intelligence can be divided in various types, there are mainly two
types of main categorization which are based on capabilities and based on
functionally of AI. Following is flow diagram which explain the types of AI.
 Types of AI based on capabilities
AI type-1: Based on Capabilities
• 1. Weak AI or Narrow AI:
• Narrow AI is a type of AI which is able to perform a dedicated task with
intelligence.The most common and currently available AI is Narrow AI in the
world of Artificial Intelligence.
• Narrow AI cannot perform beyond its field or limitations, as it is only trained
for one specific task. Hence it is also termed as weak AI. Narrow AI can fail in
unpredictable ways if it goes beyond its limits.
• IBM's Watson supercomputer also comes under Narrow AI, as it uses an
Expert system approach combined with Machine learning and natural
language processing.
• Some Examples of Narrow AI are playing chess, purchasing suggestions on e-
commerce site, self-driving cars, speech recognition, and image recognition.
 Types of AI cont’d
2. General AI:
• General AI is a type of intelligence which could perform any intellectual task with efficiency like a human.
• The idea behind the general AI to make such a system which could be smarter and think like a human by its
own.
• Currently, there is no such system exist which could come under general AI and can perform any task as
perfect as a human.
• The worldwide researchers are now focused on developing machines with General AI.
• As systems with general AI are still under research, and it will take lots of efforts and time to develop such
systems.
3. Super AI/strong AI:
• Super AI is a level of Intelligence of Systems at which machines could surpass human intelligence, and can
perform any task better than human with cognitive properties. It is an outcome of general AI.
• Some key characteristics of strong AI include capability include the ability to think, to reason,solve the puzzle,
make judgments, plan, learn, and communicate by its own.
• Super AI is still a hypothetical concept of Artificial Intelligence. Development of such systems in real is still
world changing task.
Types of AI cont’d
 Types of AI based on functionality
1. Reactive Machines
• Purely reactive machines are the most basic types of Artificial Intelligence.
• Such AI systems do not store memories or past experiences for future actions.
• These machines only focus on current scenarios and react on it as per possible best action.
• IBM's Deep Blue system is an example of reactive machines.
• Google's AlphaGo is also an example of reactive machines.
2. Limited Memory
• Limited memory machines can store past experiences or some data for a short period of time.
• These machines can use stored data for a limited time period only.
• Self-driving cars are one of the best examples of Limited Memory systems. These cars can store recent speed of nearby cars,
the distance of other cars, speed limit, and other information to navigate the road.
3. Theory of Mind
• Theory of Mind AI should understand the human emotions, people, beliefs, and be able to interact socially like humans.
• This type of AI machines are still not developed, but researchers are making lots of efforts and improvement for developing
such AI machines.
• 4. Self-Awareness
• Self-awareness AI is the future of Artificial Intelligence. These machines will be super intelligent, and will have their own
consciousness, sentiments, and self-awareness.
• These machines will be smarter than human mind.
• Self-Awareness AI does not exist in reality still and it is a hypothetical concept.
 Goals of AI
General AI goals
(A) Systems that think like humans (B). Systems that think rationally • Replicate human intelligence
• Solve knowledge intensive task.
The exciting new effort to make The study of mental faculties through the use • Make an intelligent connection
computers think . . . machines with of computational models" (Charniak and between perception and
action.
minds, in the full and literal sense" McDermott, 1985) • Enhance human-human,
(Haugeland, 1985) "The study of the computations that make it human-computer and
"[The automation of] activities that we possible to perceive, reason, and act" (Winston, computer to computer
associate with human thinking, 1992) interaction/ communication
activities such as
decision-making, problem solving, Engineering based AI Goals
learning • Develop concepts, theory and
..."(Bellman, 1978) practice of building intelligent
machines.
(C) Systems that act like humans (D). Systems that act rationally
"The art of creating machines that perform "A field of study that seeks to explain and Science based AI goals
• Develop concepts, mechanisms
functions that require intelligence when emulate intelligent behavior in terms of and vocabulary to understand
performed by people" (Kurzweil, 1990) computational processes" (Schalkoff, 1 990) biological intelligent behaviour.
"The study of how to make computers do "The branch of computer science that is
things concerned Emphasis is on understanding
at which, at the moment, people are with the automation of intelligent behavior" intelligent behaviour.
better" (Rich and Knight, 1 991 ) (Luger and Stubblefield, 1993)
 Approaches to Artificial Intelligence

• The approaches used in AI are based on the goals of the computational,

model, and the basis for evaluating performance of the system.
Human Being Rationally
Cognitive science:
• Think human-like
The goal is not just to produce human-like behaviour
but to produce a sequence of steps of the reasoning
process, similar to the steps followed by a human in
Think (1)Cognitive science approach (2) Laws of thought solving the same task.
approach Laws of thought:
• Think Rationally
• The goal is to formalize the reasoning process as a
system of logical rules and procedures for inference.
Turing test:
• creating machines that perform function requiring
intelligence when performed by people
• Goal is to develop systems that are human-like
Act (3) Turing test approach 4) Rational agent
approach Rational agent approach:
• Tries to explain and emulate intelligent behavior in
terms of computational processes, i.e automation of
intelligence
• Goal is to develop systems that are rational and
sufficient
 AI techniques
Intelligent techniques Describe and match: Model is a description of system behavior
Constraint satisfaction: Constraint is a logical relation among variables, e.g. “circle is
inside the square.
a) Describe and match d) Goal reduction Constraint satisfaction is the process of finding a solution to a set of Constraints
Generate and test method: It first guesses the solution and then test whether this
b) Constraint satisfaction e) Tree Searching solution is correct, means solution satisfies the constraint
c) Generate and test f) Rule based systems Goal reduction: The process involves the Hierarchical sub-division of goals into sub
goals, until the sub-goals which have an immediate solution are reached and are said
goal has been satisfied
Tree searching: Many problems can be described in the form of a search tree. A
solution to the problem is obtained by finding a path through this tree
Rule based systems: Rules are of the form: IF condition THEN action.
Biology-inspired techniques
Neural networks: Neural Networks model a brain learning by example.
• Neural Networks NN are structures trained to recognize input pattern
• Reinforcement learning Genetic algorithm: They are implemented as computer simulation
where techniques are inspired by evolutionary biology
• Genetic Algorithms
Knowledge representation

• Knowledge and Representation are distinct entities that play a central but
distinguishable roles in intelligent system.
• Knowledge is a description of the world. It determines a system's
competence by what it knows.
• Representation is the way knowledge is encoded. It defines the
performance of a system in doing something.
• The Knowledge Representation models/mechanisms are often based on:
• Logic
• Rules
• Frames
• Semantic Net
Logical Artificial Intelligence
• Logic is a language for reasoning; a collection of rules used while
doing logical reasoning. Types of logic:
• Preposition logic- logic of sentences -Prepositions are "sentences";
either true or false but not both
• predicative logic- Logic of objects-Predicate is a function may be true
or false for arguments
• Fuzzy logic- dealing with fuzziness-
• Temporal logic, etc.
• Preposition logic and Predicate logic are fundamental to all logic.
Search techniques
• most fundamental are
Depth first
Hill climbing
Breadth First
Least cost
Search algorithms
• Generate and Test Search
• Best-first Search
• Greedy Search
• A* Search
• Constraint Search
• Means-ends analysis
• Hill Climbing
• Heuristic Search
Hierarchical Representation of Search Algorithms
Informed search/intelligent/heuristic
Uninformed search/blind/exhaustive/brute-force
• Depth-first
• Breadth-first
• Non-deterministic search
• Iterative deepening
• Bi-directional search
 Pattern recognition
• The science that concerns the description or classification (recognition) of measurement.
• Pattern recognition problem
• Machine vision-Visual inspection.
• Character recognition-mail sorting, processing bank cheques.
• Computer aided diagnosis- Medical image.
• Speech recognition- Human computer interaction, access.
Approaches for Pattern recognition.
• Template Matching: Match with stored template considering translation, rotation and scale change, measure similarity based on
training set. Measure “Similarity” (correlation) based on training set.
• Statistical classification: Each pattern is represented in terms of features and viewed as a point in a dimensional space. Using
training sets establish decision boundaries in the feature space following “decision theoretic” or “discriminate analysis”
approaches.
• Syntactic or Structural matching: Complex pattern is composed of sub-pattern and the relations; they themselves are built from
simpler elementary sub-pattern called primitives.
The patterns are viewed as sentences belonging to a language, primitives are viewed as the alphabet of the language. The
sentences are generated according to a grammar.
• Neural networks: They are viewed as weighted directed graphs in which the nodes are artificial neurons and directed edges
(with weights) are connections between neurons input-output.
Neural networks have the ability to learn complex nonlinear input-output relationships from the sequential training procedures,
and adapt themselves to input data.
 AI languages
• IPL: was the first language developed for artificial intelligence. It includes features intended to support
programs that could perform general problem solving, including lists, associations, schemas (frames),
dynamic memory allocation, data types, recursion, associative retrieval, functions as arguments,
generators (streams), and cooperative multitasking.
•
Lisp: is a practical mathematical notation for computer programs based on lambda calculus. Linked lists
are one of Lisp languages' major data structures, and Lisp source code is itself made up of lists. As a result,
Lisp programs can manipulate source code as a data structure, giving rise to the macro systems that allow
programmers to create new syntax or even new domain-specific programming languages embedded in
Lisp. There are many dialects of Lisp in use today, among them are Common Lisp, Scheme, and Clojure.
• Prolog: is a declarative language where programs are expressed in terms of relations, and execution
occurs by running queries over these relations. Prolog is particularly useful for symbolic reasoning,
database and language parsing applications. Prolog is widely used in AI today.
• STRIPS: is a language for expressing automated planning problem instances. It expresses an initial state,
the goal states, and a set of actions. For each action preconditions (what must be established before the
action is performed) and post-conditions (what is established after the action is performed) are specified.
• Planner is a hybrid between procedural and logical languages. It gives a procedural interpretation to
logical sentences where implications are interpreted with pattern-directed inference.