 |
The phrase AI, which was coined by John McCarthy three decades ago. The phrase “AI” thus c bane defined as the simulation of human intelligence on a machine, so as to make the machine efficient to identify and use the right piece of “Knowledge” at a given step of solving a problem. Thus, AI alternatively may be stated as a subject dealing with computational models that can think and act rationally. Artificial intelligence is the process of creating machines that can act in a manner that could be considered by humans to be intelligent. This could be exhibiting human characteristics, or much simpler behaviours such as the ability to survive in dynamic environments.
The computers of the current (fifth) generation can process natural languages, play Games, recognize images of objects and prove mathematical theorems, all of which lie in the domain of Artificial Intelligence (AI).
Machine learning, perception and planning these are the main concepts provided by the AI. A little thinking, however, reveals that a system that can reason well must be a successful planner, as planning in many circumstances is part of a reasoning process. Further, a system can act rationally only after acquiring adequate knowledge from the real world. So, perception that stands for building up of knowledge from real world information is a prerequisite feature for rational actions. One step further thinking envisages that a machine without learning capability cannot possess perception. The rational action of an agent (actor), thus, calls for possession of all the elementary characteristics of intelligence. Relating AI with the computational models capable of thinking and acting rationally, therefore, has a pragmatic significance
2.2 Characteristic Requirements for the Realization of the Intelligent Systems
The AI problems, irrespective of their type, possess a few common characteristics. Identification of these characteristics is required for designing a common framework for handling AI problems. It is clear from the previous discussions that a general purpose intelligent machine should be able to perform both symbolic and numeric computations on a common platform. Symbolic computing is required in automated reasoning, recognition, matching and inductive as well as analogy-based learning. The need for symbolic computing was felt since the birth of AI in the early fifties. Recently, the connectionist approach for building intelligent machines with structured models like artificial neural nets is receiving more attention. The Artificial Neural Network (ANN) based models have successfully been applied in learning, recognition, and optimization and also in reasoning problems involved in expert systems. The ANNs have outperformed the classical approach in many applications, including optimization and pattern classification problems.
2.3 Architecture for AI Machines
During the developmental phase of AI, machines used for conventional programming were also used for AI programming. However, since AI programs deal more with relational operators than number crunching, the need for special architectures for the execution of AI programs was felt. Gradually, it was discovered that due to non-determinism in the AI problems, it supports a high degree of concurrent computing. The architecture of an AI machine thus should allow symbolic computation in a concurrent environment. Further, for minimizing possible corruption of program resources (say variables or procedures), concurrent computation may be realized in a fine grain distributed environment. Currently PROLOG and LISP “machines” are active areas of AI research, where the emphasis is to incorporate the above issues at the hardware and software levels. Most of these architectures are designed for research laboratories and are not available in the open commercial market to date. We hope for a better future for AI, when these special architectures will find extensive commercial exploitation.
2.4 Different Fields Under A.I.
2.5 Basic concepts On Neural Networks
2.5.1 Neural Processing
How do we recognize a face in a crowd? How does an economist predict the direction of interest rates? Faced with problems like these, the human brain uses a web of interconnected processing elements called neurons to process information. Each neuron is autonomous and independent; it does its work asynchronously, that is, without any synchronization to other events taking place. The two problems posed, namely recognizing a face and forecasting interest rates, have two important characteristics that distinguish them from other problems: First, the problems are complex, that is, you can’t devise a simple step-by-step algorithm or precise formula to give you an answer; and second, the data provided to resolve the problems is equally complex and may be noisy or incomplete The vast processing power inherent in biological neural structures has inspired the study of the structure itself for hints on organizing human-made computing structures. Artificial neural networks, the subject of this report covers the way to organize synthetic neurons to solve the same kind of difficult, complex problems in a similar manner as we think the human brain may. This chapter will give you a sampling of the terms and nomenclature used to talk about neural networks. These terms will be covered in more depth in the chapters to follow.
Technorati Tags: 
