Sunteți pe pagina 1din 30

Submitted by:Shinjani goyal Rollno= 34

ARTIFICIAL INTELLIGENCE
The ability of a computer or other machine to perform actions thought to require intelligence. Among these actions are logical deduction and inference, creativity, the ability to make decisions based on past experience or insufficient or conflicting information, and the ability to understand spoken language.

INTELLIGENCE BEHAVIOUR
It is the ability to learn from experiences and apply knowledge acquired from experience, handle complex situations, solve problem when important information is missing, determine what is important, react quickly and correctly to a new situation.

GOALS OF ARTIFICIAL INTELLIGENCE


Understand the principles that make intelligence possible. Developing intelligent machines or agents. Formalizing knowledge and mechanizing reasoning in all areas of human endeavor. Making the working on computers as easy as working with people. Developing human-machine systems that exploit the complementariness of human and automated reasoning.

VARIOUS APPLICATIONS OF A.I.


Neural network. Expert system. Game playing. Knowledge representation. Natural language understanding and processing. Robotics.

ROBOTICS
It involves developing mechanical or computer devices that perform task require higher degree of precision or thar are hazardous for humans. The rover was remote controlled robot used by NASA to explore surface of MARS.

SPOT AND FRESH KITTY ROBOTS

Fresh Kitty
Modular, inexpensive, autonomous mobile robot 4 wheel toy car design Max. speed of 1 foot/sec On-board microcomputer supervises and supports the exchange of information Rotating turret holds 4 sonars Turret also holds an infrared sensor to detect infrared rays 32 light sensors detect objects in front of the robot Bumpers all around the robot used to follow walls Radio modem to communicate with remote agents

SPOT
Autonomous mobile robot 2 independent wheel design Max. speed of 1 foot/sec On-board microcontroller supervises and supports the exchange of information Turret that holds infrared emitters that can be detected at a distance of up to 20 feet Bumpers all around the robot used to follow walls Radio modem to communicate with remote agents

How do SPOT and Fresh Kitty work together?


SPOT also holds a small brush on its back SPOT finds a wall and uses its bumper system and sensors to follow edges and collect dust with its brush Through radio frequency and infrared communication SPOT can bring the dust back to Fresh Kitty who has a vacuum cleaner waiting to suck it up

NEURAL NETWORK
It basically aims at mimicking the structure and functioning of the human brain, to create intelligent behaviour. It involves an attempt to build a silicon-based electronic network that is modelled on the working and form of the human brain. Our brain is a network of billions of neurons, each connected with the other. At an individual level, a neuron has very little intelligence, in the sense that it operates by a simple set of rules, conducting electric signals through its network. However, the combined network of all these neurons creates intelligent behaviour that is unrivalled and unsurpassed.

The researchers created network of electronic analogues of a neuron, based on Boolean logic. Memory was recognized to be an electronic signal pattern in a closed neural network. The neural networks developed have the ability to learn patterns and remember.

CASE STUDY FOR NEURAL NETWORK


1. 2. 3. 4. 5. Image pyramid used to locate faces of different sizes Image lighting compensation Neural Network detects rotation of face candidate Final face candidate de-rotated ready for detection. Submit image to Neural Network a. Break image into segments b. Each segment is a unique input to the network c. Each segment looks for certain patterns (eyes, mouth, etc) Output is likelihood of a face.

6.

EXPERT SYSTEM
The expert systems involves designing intelligent machines that solve problems by deductive logic. This is an intensive approach as opposed to the extensive approach in neural networks. As the name expert systems suggest, these are machines devoted to solving problems in very specific niche areas. They have total expertise in a specific domain of human thought. Their tools are like those of a detective or sleuth. They are programmed to use statistical analysis and data mining to solve problems. They arrive at a decision through a logical flow developed by answering yes-no questions.

Expert system Develop-ment Process

CASE STUDY FOR EXPERT SYSTEM- PROSPECTOR


Developed by Hart and Duda of SRI International. It is a consultation system to assist geologists working in mineral exploration. It attempts to represent the knowledge and reasoning process of experts in the geological domain. The user of this system is a exploration geologist. The user uses it in initial stages of investigating a possible drilling site.

The geologists provide conclusions based on their study.

Prospector compares observations with stored models of core deposits.

Prospector then notes the similarities, differences .

It then assesses the mineral potential of the prospect.

Working of a prospector

GAME PLAYING
Game artificial intelligence refers to techniques used in computer and video games to produce the illusion of intelligence in the behavior of nonplayer characters (NPCs). Game playing is a search problem defined by: 1. Initial state 2. Successor function 3. Goal test 4. Path cost function

CHARACTERISTICS OF GAME PLAYING


oUnpredictable opponent The solution is a strategy specifying a move for every possible opponent reply. oTime limits Must be approximated in case of unable to find the goal

CASE STUDY FOR GAME PLAYING- COMPUTER CHESS


The first game for which AI was used to create a computer controlled opponent was chess . The way that AI in chess programs often works is by using a large search tree of possible states, as well as databases of played chess games, with a focus on variations of openings and end games. The AI part is mainly involved with the search heuristics that are employed for evaluating the positions in the search tree. Some modern chess-playing programs can analyse millions of different positions per second.

In chess, basically each move is modelled as a branch in a tree. Alternate levels in the tree indicate alternate players' moves, and as they make choices the game progresses down the tree. For chess, each node in the tree represents a specific board configuration. This tree is a very small part of the huge search space we discussed in the previous page. It's called a search tree. Basically, the computer needs to look through that to find the best possible option. But how does it know the best branch to take?

Evaluation
Instead of going all the way to the leafs of the tree, we stop at a specific node, and try to estimate how good this situation is. This is usually enough to indicate if the branch should be chosen or not. Typically, an evaluation function is handcrafted by an expert. All the experience and knowledge is crammed into a small equation that tells the search how good a node is. A minimax search algorithm can do this. The evaluation is used at each node in the tree to obtain a reward value for each player (although one value can be enough in zero sum games: a win on one side implies a loss on the other). The minimax algorithm alternatively tries to maximise the advantage of one player, and minimise the reward of the other player at consecutive levels of the tree.

NATURAL LANGUAGE PROCESSING


Natural language processing gives machines the ability to read and understand the languages that humans speak. A sufficiently powerful natural language processing system would enable natural language user interfaces and the acquisition of knowledge directly from human-written sources, such as Internet texts. Some straightforward applications of natural language processing include information retrieval. A common method of processing and extracting meaning from natural language is through semantic indexing.

Naturally occurring texts can be of any language, mode, genre, etc. The texts can be oral or written. The only requirement is that they be in a language used by humans to communicate to one another. Also, the text being analyzed should not be specifically constructed for the purpose of the analysis, but rather that the text be gathered from actual usage.

A full NLU System should be able to:


1. Paraphrase an input text 2. Translate the text into another language 3. Answer questions about the contents of the text 4. Draw inferences from the text

KNOWLDEGE REPRESENTATION
A subarea of Artificial Intelligence concerned with understanding, designing, and implementing ways of representing information in computers so that programs (agents) can use this information to derive information that is implied by it, to converse with people in natural languages, to decide what to do next to plan future activities, to solve problems in areas that normally require human expertise.

REQUIREMENT FOR A KNOWLEDGE REPRESENTATION SYSTEM


A good knowledge representation system for any particular domain should possess the following properties: Representational adequacy the ability to represent all the different kinds of knowledge that might be needed in that domain Inferential adequacy the ability to manipulate the representational structures to derive new structures (corresponding to new knowledge) from existing structures. Inferential efficiency the ability to incorporate additional information into the knowledge structure which can be used to focus the attention of the inference mechanisms in the most promising directions. Acquisitional efficiency that specifies the access procedures that enables ways of creating and modifying representations and answering questions using them, i.e how we generate and compute things with the representation

REFRENCES
Artificial intelligence by Anita Deshpande Wikipedia webcache.googleusercontent.com www.cse.buffalo.edu www.scribd.com

S-ar putea să vă placă și