it assisgnment

8/3/2019 IT Assisgnment

http://slidepdf.com/reader/full/it-assisgnment 1/29

Arjit Jaiswal 12212Jose Tom 12225Mayank Gupta 12228Rishabh Sultania 12241

Prateek Jain 12238Joel Pinto 12223

Presented By:



Your own sub headline

ARTIFICIAL INTELLIGENCE

The study and design

of intelligent agentswhere an intelligentagent is a system thatperceives itsenvironment and takes

actions that maximizeits chances of success.

AI

Artificialintelligence (AI) isthe intelligence ofmachines and thebranch of computer

science that aimsto create it.

AI

1 2



HISTORY

• Mechanical or "formal" reasoning has been developed byphilosophers and mathematicians since antiquity.

• The field of AI research was founded at a conference on the campusof Dartmouth College in the summer of 1956

• In the early 1980s, AI research was revived by the commercialsuccess of expert systems, a form of AI program that simulated the

knowledge and analytical skills of one or more human experts.• By 1985 the market for AI had reached over a billion dollars

• On 11 May 1997, Deep Blue became the first computer chess-playing system to beat a reigning world chess champion, GarryKasparov.



HISTORY CONT.

• In 2005, a Stanford robot won the DARPA Grand Challenge bydriving autonomously for 131 miles along an unrehearsed desert

trail• In February 2011, in a Jeopardy! quiz show exhibition match, IBM's

question answering system, Watson, defeated the two greatestJeopardy! champions, Brad Rutter and Ken Jennings, by asignificant margin

• The Kinect which provides a 3D body –motion interface for the Xbox360 uses algorithms that emerged from lengthy AI research, but fewconsumers realize the technology source.

• AI applications are no longer the exclusive domain of Department ofdefense R&D, but are now common place consumer items and

inexpensive intelligent toys.



The traits described below have received the most attention

TRAITS

• Learning

• Natural

languageprocessing

• Motion andmanipulation

• Perception

TRAITSTRAITS

• Socialintelligence

• Creativity

• Generalintelligence

TRAITS

• Deduction,reasoning,

problem solving

• Knowledgerepresentation

• Planning



Deduction, reasoning, problem solving

• Early AI researchers developed algorithms that imitated the step-by-step reasoning that humans use when they solve puzzles or make

logical deductions• AI research developed highly successful methods for dealing with

uncertain or incomplete information, employing concepts fromprobability and economics.

• Human beings solve most of their problems using fast, intuitive

judgments rather than the conscious, step-by-step deduction thatearly AI research was able to model.

• AI emphasized the importance of sensorimotor skills to higherreasoning; neural net research attempts to simulate the structuresinside human and animal brains that give rise to this skill.



Knowledge representation

http://en.wikipedia.org/wiki/File:GFO_taxonomy_tree.png



Planning

http://en.wikipedia.org/wiki/File:Hierarchical-control-system.svg



Cont.

• In classical planning problems, the agent can assume that it is theonly thing acting on the world and it can be certain what the

consequences of its actions may be.• Multi-agent planning uses the cooperation and competition of many

agents to achieve a given goal. Emergent behaviour such as this isused by evolutionary algorithms and swarm intelligence.



Learning

• Machine learning has been central to AI research from thebeginning.

• In 1956, at the original Dartmouth AI summer conference, RaySolomon off wrote a report on unsupervised probabilistic machinelearning: "An Inductive Inference Machine". Unsupervised learning isthe ability to find patterns in a stream of input

• Supervised learning includes both classification and numerical

regression.• Regression is the attempt to produce a function that describes the

relationship between inputs and outputs and predicts how theoutputs should change as the inputs change



Natural Language Processing

• Natural language processing gives machines the ability to read andunderstand the languages that humans speak.

• Some straightforward applications of natural language processinginclude information retrieval(or text mining) and machine translation.



Motion and Manipulation

• The field of robotics is closely related to AI.

• Intelligence is required for robots to be able to handle such tasks as

object manipulation and navigation,

• with sub-problems of

• localization (knowing where you are),

• mapping (learning what is around you) and

•motion planning (figuring out how to get there).



Perception

• Machine perception is the ability to use input from sensors (such ascameras, microphones, sonar and others more exotic) to deduce

aspects of the world.• Computer vision is the ability to analyze visual input.

• A few selected subproblems are speech recognition, facialrecognition and object recognition



Social intelligence

Kismet, a robot with rudimentary social skills

http://en.wikipedia.org/wiki/File:Kismet_robot_at_MIT_Museum.jpg



Cont.

• Emotion and social skills play two roles for an intelligent agent. First,it must be able to predict the actions of others, by understanding

their motives and emotional states. (This involves elements of gametheory, decision theory, as well as the ability to model humanemotions and the perceptual skills to detect emotions.)

• For good human-computer interaction, an intelligent machine needs

to display emotions. At the very least it must appear polite andsensitive to the humans it interacts with. At best, it should havenormal emotions itself.



Creativity

• A sub-field of AI addresses creativity both theoretically (from aphilosophical and psychological perspective) and practically (via

specific implementations of systems that generate outputs that canbe considered creative, or systems that identify and assesscreativity).

• A related area of computational research is Artificial intuition andArtificial imagination.



General Intelligence

• Most researchers hope that their work will eventually beincorporated into a machine with general intelligence (known as

strong AI), combining all the skills above and exceeding humanabilities at most or all of them. A few believe that anthropomorphiclike artificial consciousness or an artificial brain may be required forsuch a project.

• Many of the problems above are considered AI-complete: to solve

one problem, you must solve them all. For example, even astraightforward, specific task like machine translation requires thatthe machine follow the author's argument (reason), know what isbeing talked about (knowledge), and faithfully reproduce the author'sintention (social intelligence). Machine translation, therefore, is

believed to be AI-complete: it may require strong AI to be done aswell as humans can do it



Tools

• In the course of 50 years of research, AI has developed a largenumber of tools to solve the most difficult problems in computer

science. A few of the most general of these methods are discussedbelow

1. Search and optimization:Includes

Search algorithms such as

BFS(Breadth First Search)

DFS(Depth First Search)

Heuristic Search

Mathematical optimization:Blind-Hill Climbing Evolutionarycomputation



Logic

• Logic is used for knowledge representation and problem solving,but it can be applied to other problems as well. For example, the

satplan algorithm uses logic for planning and inductive logicprogramming is a method for learning and Propositional or sententiallogic is the logic of statements which can be true or false.



Neural Network

http://en.wikipedia.org/wiki/File:Artificial_neural_network.svg



Neural Network

• A neural network is an interconnected group of nodes, akin to the

vast network of neurons in the human brain.• The main categories of networks are acyclic or feed forward neural

networks (where the signal passes in only one direction) andrecurrent neural networks (which allow feedback).

• Among recurrent networks, the most famous is the Hopfield net, a

form of attractor network, which was first described by John Hopfieldin 1982



Control Theory

• Control theory, the grandchild of cybernetics, has many importantapplications, especially in robotics.



Language

• AI researchers have developed several specialized languages for AIresearch, including Lisp and Prolog



Applications of AI

You can buy machines that can play master level chess for a fewhundred dollars.

Game playing

In the 1990s, computer speech recognition reached a practical level for limitedpurposes. Thus United Airlines has replaced its keyboard tree for flightinformation by a system using speech recognition of flight numbers and citynames. It is quite convenient

Speech recognition

A ``knowledge engineer'' interviews experts in a certain domain and tries toembody their knowledge in a computer program for carrying out some task. Oneof the first expert systems was MYCIN in 1974, which diagnosed bacterialinfections of the blood and suggested treatments.

Expert systems

1

2

3



Applications of AI Cont.…

Applications of real-time intelligent automation, and their associated

supporting methodologies and techniques.

Decision-support systems.

Architectures, algorithms and techniques for distributed AI systems.

Knowledge processing, e.g. a priori and self-learning, knowledgerepresentation, knowledge compaction, knowledge bases, expertsystems, neural networks etc…

Fault detection, fault analysis and diagnostics.

Perception, e.g. image and signal processing, pattern recognition,vision systems, tactile systems, and speech recognition and synthesis.




Transportation

HeavyIndustry

Hospitals

FinanceBanks use artificial intelligence systems to organize operations,invest in stocks, and manage properties. In August 2001, robots

beat humans in a simulated financial trading competition.

A medical clinic can use artificial intelligence systems to organizebed schedules, make a staff rotation, and provide medicalinformation

Robots are often given jobs that are considered dangerous to humans.Robots have proven effective in jobs that are very repetitive which maylead to mistakes or accidents due to a lapse in concentration and otherjobs which humans may find degrading.

Fuzzy logic controllers have been developed for automatic gearboxes inautomobiles (the 2006 Audi TT, VW Toureg and VW Caravell feature theDSP transmission which utilizes Fuzzy logic, a number of Škoda variants(Škoda Fabia) also currently include a Fuzzy Logic based




Music

NewsPublishing

Toys &Games

Telecommunication

Many telecommunications companies make use of heuristicsearch in the management of their workforces, for example BT

Group has deployed heuristic search in a scheduling applicationthat provides the work schedules of 20,000 engineers.

The first widely released robot, Furby. A mere year later animproved type of domestic robot was released in the form of Aibo,a robotic dog with intelligent features and autonomy. AI has also

been applied to video games.

The company Narrative Science makes computer generated news andreports commercially available, including summarizing team sportingevents based on statistical data from the game. It also creates financialreports and real estate analyses

With AI, scientists are trying to make the computer emulate the activitiesof the skilful musician. Composition, performance, music theory, soundprocessing are some of the major areas on which research in Music andArtificial Intelligence are focusing.



THANK YOU!

Your Logo

it assisgnment

Documents