Download Turing Test - ritesh sharma

Artificial Intelligence
=
Artificial ( Non natural ) + Intelligence
Intelligence means




Ability to acquire the knowledge , apply the knowledge and retain the knowledge
Ability to make decisions
Ability to apply the logic
Respond Quickly to new situations
Artificial Intelligence : It is the branch of computer science which deals with developing artificial
machines with intelligence . This term is introduced by John McCarthy in 1956 (He is known as father of AI ).
History Of AI
1923
Karel Čapek play named “Rossum's Universal Robots” (RUR) opens in London, first use of the word
"robot" in English.
Alan Turing introduced Turing Test
1950
John McCarthy coined the term Artificial Intelligence.
1956
The Deep Blue Chess Program (IBM) beats the then world chess champion, Garry Kasparov.
1997
Turing Test
Turing want to answer the question can machine think ???? For this he perform Turing test in 1950 .At that
time no computer was able to pass . If 30% OF Human Interrogator gets failed to differentiate between
Human and computer than we say that computer passed Turing Test
A computer program called Eugene Goostman, which simulates a 13-year-old Ukrainian boy, is said to have
passed the 65 years old Turing Test at the renowned Royal Society in London in 2014
CAPTCHA - Completely Automated Public Turing Test To Tell Computers And Humans Apart
Types Of AI
Strong AI : Aims to build a machine which can truly reason and solve the problem .These machines are self
aware and their ability is indistinguishable from human intelligence
Weak AI :- Aims to build a machine which act as if they are intelligent but cannot truly reason and cannot
solve all the problems
Applied AI : To built commercially smart systems like automatic doors etc.
Cognative AI: Test the theories behind how human mind work. Neural Network comes under this category
Applications of AI
Gaming − AI plays crucial role in strategic games such as chess, tic-tac-toe, etc., where machine can think of
large number of possible positions based on heuristic knowledge.
Expert Systems − There are some applications which integrate software and special information and they
provide explanation and advice to the users.
Computer Vision − Subfield of Artificial Intelligence . Purpose of computer vision is to program a computer to
understand a scene or feature in an image
Speech Recognition
Handwriting Recognition − The handwriting recognition software reads the text written on paper by a pen or
on screen by a stylus. It can recognize the shapes of the letters and convert it into editable text.
Intelligent Robots − Robots are able to perform the tasks given by a human. They have sensors to detect
physical data from the real world such as light, heat, temperature, movement e.t.c. They have efficient
processors, multiple sensors and huge memory, to exhibit intelligence. In addition, they are capable of learning
from their mistakes and they can adapt to the new environment.
Some Problems :
There are some tasks which are mundane tasks that we do in our daily life (Recognizing Faces,
Communicating Through natural Languages, Navigating through obstacles in path ) and there are some
tasks that we consider intelligent ( Medical Diagnoses , Playing games , Solving math puzzles )
Now which of these problems are easy for the computer to do and which of these problems are hard ???
It has been easier to solve intelligent tasks easily by AI but AI has not had the same amount of success in
dealing with mundane tasks.
Agent and Environment
Agent : Perceives ( gets ) information from environment through sensors and based on that information
acts upon environment through actuators
Agent program implement mapping from percept sequence to actions
Examples Of agents
1. Humans :
Sensors: Eyes, Ears , Taste ,Smell , Touch
Actuators: Hands ,Legs ,etc
2. Robots :
Sensors: Camera, Infrared sensors
Actuators: Lights ,Wheels ,Speakers
Intelligent Agent ( 4 things ):
1.
2.
3.
4.
Must sense
Must act
Must be autonomous
Must be rational
Autonomous Agent :- Which decide autonomously which action to take in current situation to maximize
progress towards goal .
Rational Agent : Rational agent is the agent which always does the right thing . AI is all about building ration
agents.
1. Perfect Rationality Assumes that rational agent is omniscient (knows everything ). We do not come
under this category . In reality rational agent is not omniscient because it does not know the actual
outcome of actions and it may not know certain aspects of environment.
2. Bounded Rationality : Assumes that rational agent uses approximate methods to handle tasks
Environment can be defined in many different ways
On the basis Of Observability
1. Fully Observable : All of relevant portion of environment is observable.
For example, consider an agent playing chess like the deep blue chess playing program. The agent has
complete knowledge of the board. So everything about the environment is accessible to the agent. So the
chess environment is a fully observable environment
2. Partially Observable : Not all of the relevant portion of environment is observable.
For example, consider again the environment where the agent is playing pokers where the agent
cannot see the hand of the opponent. So the environment in this case is only partially observable to the
agent. So, if the environment is partially observable the agent in order to behave successfully in such an
environment has an added task of keeping track of the environment
On the basis Of Determinism
1. Deterministic environments: In deterministic environments the next state of the environment is
completely described by the current state and the agent’s action. E.g Crossword puzzle
2. Stochastic environment : In stochastic environments, on the other hand, there is some element of
uncertainty. Therefore how the environment changes depends not just on the action that the agent takes.
E.g Ludo . If you look at the game of Ludo it is a stochastic environment because how the environment
evolves depend on the value which the die has rolled. So whether the die has rolled 1 or 2 or 6
depending on that the agent can decide its actions. Therefore this is a truly stochastic environment.
3. Strategic environment: In a strategic environment apart from the current agent itself there are other
agents around and the actions of all these agents influence the environment. A strategic environment is
one where the environment is only changed by the actions of the agent itself and other agents. E.g
Chess
On the basis Of Episodicity
1. Episodic environment E.g Image Analysis
2. Sequential environment : E.g Chess , Poker
First of all sometimes certain tasks can be divided into different phases or different episodes. In such episodic
environments the one episode may or may not influence the subsequent episode. So, if one episode does not
influence the subsequent episode such an environment is called an episodic environment and if one episode
influence the subsequent episode such an environment is called an sequential environment
On the basis Of dynamism
1. Static environment E.g Chess , Poker , Crossword puzzle
2. Dynamic environment E.g Taxi driving
In Static environment agent need not keep looking at the world while it is deciding on the action whereas
dynamic environments continuously ask the agent what it wants to do .
On the basis Of continuity
1. Discrete E.g Chess , Poker , Crossword puzzle
2. Continuous E.g Taxi driving
In Discrete clearly defined states and actions are there whereas in continuous clearly defined states and actions
are not there
On The basis Of No Of agents
Multi Agent : E.g Chess , Poker
Single Agent : E.g Crossword puzzle