artificial intelligence

Category: Entertainment

Presentation Description

latest trends in computers


Presentation Transcript




CONTENTS History Aim Approaches Scope Branches Of AI Genetic Programming Preparatory Steps of Genetic Programming Definition Genetic Operations Executional Steps of Genetic Programming Fuzzy Logic Fuzzy Logic (contd.) Applications Problems Latest Trends Biometrics Robotics Neural Networks References


Definition It is defined as intelligence exhibited by an artificial entity.It forms a vital branch of computer science,dealing with intelligent behavior in machines. Examples:Chess playing,Speech Recognition.




History 1956-1979:Various artificial intelligence research facilities were setup at MIT and Princeton. 1980’s:In 1980 momentum started to swing upward for AI supporters with the re-invention of expert systems. 1993-Present Day:From 1993 until the turn of the century AI has reached some incredible landmarks with the creation of intelligent agents.These agents use the surrounding environment to solve the problems effectively and efficiently.


Aims To foster the development and understanding of AI. To promote interdisciplinary exchanges between AI and other fields of information processing. To contribute to the overall aims and objectives for further development.


Approaches Field of AI can be divided into two broad categories: Bottom-Up approach: - Build electronic replicas of the human brain's complex network of neurons. (e.g. Artificial Neural Network) Top-Down approach: - It attempts to mimic the brain's behavior with computer programs. (e.g. Genetic Programming, Fuzzy Logic)


Scope It provides a wide range of techniques,which can be applied to wide range of application areas. -Automated Reasoning - Belief Revision -Computer Vision -Data Mining

Branches of AI:

Branches of AI Pattern Recognition Inference Planning Ontology Heuristics Genetic Programming Logical AI

Genetic Programming:

Genetic Programming Genetic programming is an automated method for creating a working computer program from a high-level problem statement of a problem. It achieves this goal of automatic programming by genetically breeding a population of computer programs using the principle of Darwinian natural selection and biologically inspired operations.

Genetic Programming:

Genetic Programming

Preparatory Steps of Genetic Programming:

Preparatory Steps of Genetic Programming The set of terminals (e.g., the independent variables of the problem) for each branch of the to-be-evolved program. The set of primitive functions for each branch of the to-be-evolved program. The fitness measure. Certain parameters for controlling the run. The termination criterion and method for designating the result of the run.

Genetic Operations:

Genetic Operations Crossover : - Create new offspring program(s) for the new population by recombining randomly chosen parts from two selected programs Mutation : - Create one new offspring program for the new population by randomly mutating a randomly chosen part of one selected program. Reproduction: - Copy the selected individual program to the new population. Architecture Altering operations : - Choose an architecture-altering operation from the available repertoire of such operations and create one new offspring program for the new population by applying the chosen architecture-altering operation to one selected program.

Executional Steps of Genetic Programming:

Executional Steps of Genetic Programming Randomly create an initial population. Iteratively perform the following steps until the termination criterion is satisfied: Execute each program in the population and ascertain its fitness using the problem’s fitness measure. Select one or two individual program(s) from the population with a probability based on fitness (with reselection allowed) to participate in the genetic operations. Create new individual program(s) for the population by applying genetic operations with specified probabilities. After the termination criterion is satisfied, the single best program in the population produced during the run is harvested and designated as the result of the run. If the run is successful, the result may be a solution (or approximate solution) to the problem.

Fuzzy Logic:

Fuzzy Logic "Fuzzy Logic is basically a multi-valued logic that allows intermediate values to be defined between conventional evaluations like yes/no, true/false, black/white, etc. Notions like rather warm or pretty cold can be formulated mathematically and processed by computers." Uncertainty is considered as a great utility. Newtonian Mechanics Calculus Statistical Mechanics Probability Theory

Fuzzy Logic (contd.):

Fuzzy Logic (contd.) Fuzzy Sets: - These are sets with boundaries that are not precise. The membership in a fuzzy set is not a matter of affirmation or denial, but rather a matter of degree. e.g. A day is called sunny if it has around 25% cloud cover but it can be called sunny if it is 30% also. Thus a fuzzy set representing our concept will assign a degree of membership of 1 to a cloud cover of 0%, 0.75 to a cloud cover of 20% and 0% to a cloud cover of 75%.

Applications :

Applications Game Playing Speech Recognition Computer Vision Expert Systems Virtual Reality Image Processing Artificial Creativity

Game Playing:

Game Playing

Speech Recognition:

Speech Recognition

Image Processing :

Image Processing

Virtual Reality :

Virtual Reality

Expert Systems:

Expert Systems

Artificial Creativity :

Artificial Creativity

Expert Systems:

Expert Systems

Problems of AI:

Problems of AI Mundane Tasks planning vision robotics natural language processing Expert tasks required specialized skills and training , for example Medical Diagnosis,Trouble Shooting Equipments. Formal Tasks Games Mathematics

Latest Trends:

Latest Trends Biometrics Robotics Neural Networks


BIOMETRICS It is the science and technology of measuring and analyzing the data.In Information technology it refers to the science that measure and analyze the human body characteristics. Biometric systems consists of- Scanner Software Database

Classification of Biometrics :

Classification of Biometrics Physiological Biometrics-measures the distinct traits that people have ,usually dictated by their genetics. Behavioral Biometrics-measure the distinct actions that human take,which are very hard to copy from one person to another.They measure characteristics of human body indirectly.


Applications Cellular telephone security Process control security Verification of signatures ATM transaction verification Building access control


ROBOTICS It is the science and technology of robots,their design,manufacture and applications.Robotics require a working knowledge of electronics and mechanics.


Applications Spot and electric arc welding Pick and place operations Assembly Spray finishing operations


NEURAL NETWORKS It is a massively parallel distributed processor,made up of simple processing units which has natural tendency for strong knowledge and making it available for use.

Artificial Neural Networks:

Artificial Neural Networks An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems process information. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. Human Neuron Artificial Neuron

A Simple Neuron:

A Simple Neuron An artificial neuron is a device with many inputs and one output. The neuron has two modes of operation; the training mode and the using mode. In the training mode, the neuron can be trained to fire (or not), for particular input patterns. In the using mode, when a taught input pattern is detected at the input, its associated output becomes the current output. If the input pattern does not belong in the taught list of input patterns, the firing rule is used to determine whether to fire or not.



Firing Rule of ANN:

Firing Rule of ANN The firing rule is an important concept in neural networks and accounts for their high flexibility. A firing rule determines how one calculates whether a neuron should fire for any input pattern. It relates to all the input patterns, not only the ones on which the node was trained. For example, a 3-input neuron is taught to output 1 when the input (X1,X2 and X3) is 111 or 101 and to output 0 when the input is 000 or 001. Then, according truth tables before and after applying the firing rule.`

Firing Rule of ANN (contd.):

Firing Rule of ANN (contd.) X1 0 0 0 0 1 1 1 1 X2 0 0 1 1 0 0 1 1 X3 0 1 0 1 0 1 0 1 OUT 0 0 0 0/1 0/1 1 1 1 X1 0 0 0 0 1 1 1 1 X2 0 0 1 1 0 0 1 1 X3 0 1 0 1 0 1 0 1 OUT 0 0 0/1 0/1 0/1 1 0/1 1


Benefits Non linearity Input output mapping Adaptivity Contextual information Evidential response Fault tolerance VLSI


References Artificial Intelligence,2nd Edition, ELAINE RICH and KEVIN KNIGHT(TMH) Comprehensive Overview of the Applications of Artificial Life KYUNG –JOONG KIM and SUNG -BAE CHO Artificial Intelligence by George F Luger,4 th Edition(Pearson Education).

authorStream Live Help