Artificial Intelligence

Views:
 
Category: Education
     
 

Presentation Description

Artificial Intelligence

Comments

Presentation Transcript

PowerPoint Presentation:

Prepared By:- Tank Kalpana MSc IT & CA

AGENDA:

AGENDA What is Intelligence? What is Artificial Intelligence? History Problems of AI Approach of AI Tools of AI Application of AI Dangers of AI

INTELLIGENCE :  :

INTELLIGENCE : Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines.

SYNTHETIC INTELLIGENCE :  :

SYNTHETIC INTELLIGENCE : SYNTHETIC(Artificial) intelligence is “the study and design of intelligent agents.

INTELLEGENT AGENTS :  :

INTELLEGENT AGENTS : It is a system that perceives its environment and takes actions which maximize its chances of success. AI can be seen as a realization of an abstract intelligent agent i.e AIAI.

What is artificial intelligence? :

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. A machine that replicates the functionality of the human brain. A machine that does a specific task that traditionally has been done by humans.

CONTI…:

CONTI… Artificial Intelligence (AI) can be defined as the simulation of human intelligence processes by machines, especially computer systems.

CONTI..:

CONTI.. The branch of computer science concerned with making computers behave like humans. The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology. Artificial intelligence includes Games playing : programming computers to play games such as chess and checkers

CONTI..:

CONTI.. Expert systems : programming computers to make decisions in real-life situations (for example, some expert systems help doctors diagnose diseases based on characteristics) Natural language : programming computers to understand natural human languages

CONTI..:

CONTI.. Neural networks : Systems that simulate intelligence by attempting to reproduce the types of physical connections that occur in animal brains R obotics : programming computers to see and hear and react to other sensory

HISTORY :

HISTORY The field of AI research was founded at a conference on the campus of Dartmouth College in the summer of 1956 . It including John McCarthy , Marvin Minsky , Allen Newell and Herbert Simon , became the leaders of AI research for many decades. In the early 80s, AI research was revived by the commercial success of expert systems; applying the knowledge and analytical skills of one or more human experts. By 1985 the market for AI had reached more than a billion dollars.

CONTI…:

CONTI… In the 1990s and early 21st century, AI achieved its greatest successes , Artificial intelligence is used for logistics, data mining , medical diagnosis and many other areas throughout the technology industry . On 11 May 1997, Deep Blue became the first computer chess-playing system to beat a reigning world chess champion.

CONTI..:

CONTI.. In 2005, a Stanford robot won the DARPA Grand Challenge by driving autonomously for 131 miles along an unrehearsed desert trail .

CONTI..:

CONTI.. The Kinect which provides a 3D body–motion interface for the Xbox 360 uses algorithms that emerged from lengthy AI research, but few consumers realize the technology source. In common usage, the term "AI" no longer seems to apply to off-the-shelf solved computing-science problems, which may have originally emerged out of years of AI research.

Problems of AI :  :

Problems of AI : Deduction, Reasoning, Problem solving : Deduction, Reasoning, Problem solving Early AI researchers imitated the process of step-by-step reasoning that human beings use when they solve puzzles, play board games, or make logical deductions. AI research had also developed successful methods for dealing with uncertain or incomplete information.

CONTI….:

CONTI…. Deduction, Reasoning, Problem solving Human beings solve most of their problems using unconscious reasoning, rather than the conscious(aware), step-by-step deduction that early AI research was able to model. The problem of unconscious(unaware) problem solving, which forms part of our commonsense reasoning, is largely unsolved.

Unconscious Knowledge :

Unconscious Knowledge Unconscious Knowledge Much of what people know isn't represented as "facts" or "statements" that they could actually say out loud. They take the form of intuitions or tendencies and are represented in the brain unconsciously. This unconscious knowledge informs, supports and provides a context for our conscious knowledge.

Unsupervised Learning :

Unsupervised Learning Unsupervised Learning Find a model that matches a stream of input "experiences", and be able to predict what new "experiences" to expect.

Motion & Manipulation :

Motion & Manipulation Motion & Manipulation 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).

Knowledge representation:

Knowledge representation Knowledge representation and knowledge engineering are central to AI research. Many of the problems machines are expected to solve will require extensive knowledge about the world. Among the things that AI needs to represent are: objects, properties, categories and relations between objects; situations, events, states and time; causes and effects; knowledge about knowledge

Learning:

Learning Machine learning has been central to AI research from the beginning. In 1956, at the original Dartmouth AI summer conference, Ray Solomonoff wrote a report on unsupervised probabilistic machine learning: "An Inductive Inference Machine". Unsupervised learning is the ability to find patterns in a stream of input. Supervised learning includes both classification and numerical regression .

CONTI…:

CONTI… Classification is used to determine what category something belongs in, after seeing a number of examples of things from several categories. Regression is the attempt to produce a function that describes the relationship between inputs and outputs and predicts how the outputs should change as the inputs change.

Social intelligence:

Social intelligence Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects .It is an interdisciplinary field spanning computer sciences , psychology , and cognitive science . Kismet , a robot with rudimentarysocial skills

Approaches to AI : :

Approaches to AI : Cybernetics & Brain Simulation : Cybernetics & Brain Simulation A number of researchers have explored the connection between neurology, information theory, and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary (primary) intelligence.

Artificial Neural Networks : :

Artificial Neural Networks : Artificial Neural Networks It consists of an interconnected group of artificial neurons and processes information using a connection approach to computation. In most cases an ANN is an (comfortable) that changes its structure based on external or internal information that flows through the network during the learning phase.

Knowledge based AI :

Knowledge based AI Expert Systems : An expert system, also known as a knowledge based system, is a computer program that contains the knowledge and analytical skills of one or more human experts, related to a specific subject.

CONTI..:

CONTI.. The most common form of expert system is a computer program, with a set of rules, that analyzes information about a specific class of problems, and recommends one or more courses of user action. The expert system may also provide mathematical analysis of the problem's).

AI Tools:

AI Tools In the course of 50 years of research, AI has developed a large number of tools to solve the most difficult problems in computer science . A few of the most general of these methods are discussed below. Neural Network(s) Mobile Agent System(s) Genetic Algorithms Fuzzy Logic

Neural Network(s) :

Neural Network(s) A Neural Network is an AI tool modeled by the way neurons in the human brain learns hence the name “neural”. Neural networks are designed to recognize patterns in data and predict an output from a given set of information. A classic example is the use of neural nets to predict what stocks are considered to be undervalued given all of the information about the stock at that moment in time .

CONTI…:

CONTI… Neural networks need to be trained on the data before it can predict or learn. In this way, they “learn from example” similar to the way a child learns.

Mobile Agent System(s) :

Mobile Agent System(s) A mobile agent is generally characterized by a piece of software that can go from one computer to another computer (or network) and perform some type of useful execution on the user’s behalf. You can set up agents to understand the Internet to look for something useful.

Conti..:

Conti.. For instance, a shopping agent could be set up to find a certain line of clothing in a certain size with instructions to make a purchase for the individual once a certain price criteria was met. In the B2B marketplace, agents will be programmed to deal price with other agents to execute many transactions between suppliers and customers.

Genetic Algorithms :

Genetic Algorithms A model of machine learning, which derives its behavior from a metaphor of some mechanisms of evolution in nature. This is done by modeling the way DNA Changes and adapts to varied environmental conditions within a perfect population. The individuals in the population then go through a process of simulated "evolution".

Fuzzy Logic :

Fuzzy Logic A variation of classic logic that has been extended to handle the concept of partial truth -- truth values between "completely true" and "completely false". Dr. Lotfi Zadeh of UC/Berkeley introduced it in the 1960's as a means to model the uncertainty of natural language.

Applications of AI :

Applications of AI Speech Recognition : Speech Recognition While it is possible to instruct some computers using speech, most users have gone back to the keyboard and the mouse as still more convenient.

Understanding Natural Language :  :

Understanding Natural Language : Natural language processing gives machines the ability to read and understand the languages that humans speak. Understanding Natural Language Just getting a sequence of words into a computer is not enough. The computer has to be provided with an understanding of the domain the text is about, and this is presently possible only for very limited domains. HELLO ! HELLO!!!

Game Playing :  :

Game Playing : Game Playing There is some AI in them, but they play well against people mainly through brute force computation--looking at hundreds of thousands of positions. Game Playing The most obvious is in the control of any NPCs in the game, although scripting is currently the most common means of control.

Pattern Recognition :  :

Pattern Recognition : Pattern Recognition For example, a vision program may try to match a pattern of eyes and a nose in a scene in order to find a face. More complex patterns, e.g. in a chess position are also studied. These more complex patterns require quite different methods than do the simple patterns.

Genetic Programming : :

Genetic Programming : Genetic Programming Genetic programming is a technique for getting programs to solve a task by mating random Lisp programs and selecting fittest in millions of generations.

DANGERS of AI : :

DANGERS of AI : I Hate HUMANS!!!!

SUPERINTELLIGENCE :  :

SUPERINTELLIGENCE : SUPERINTELLIGENCE Deep Blue chess program which beat world chess champion. Deep Blue searches over 200 million moves per second.. It evaluates each position and makes its choice of move based on the evaluation algorithm.

NANOMACHINES:

NANOMACHINES NANOMACHINES Human-surpassing computing power is usually estimated at 10^17 ops/sec…… even primitive noncompeting will allow to put this amount of computing power in your shirt pocket, and power it for ten watts NANOMACHINES This one an electron micrograph of an actual T4 bacteriophage infecting a bacterium. You can see its little cell puncturing device penetrating the bacterium.

PowerPoint Presentation:

Thanks For Listening!!