What is Artificial Intelligence? How is it different from Neural Networks?

 What is Artificial Intelligence? How is it different from Neural Networks?

Artificial Intelligence
Artificial Intelligence is the science and technology based on various functions to develop a system that can think and work like a human being. It is “the study and design of intelligent agents”. And intelligent agents are systems that perceive its environment and takes actions that maximize its chances of success.  It can reason, analyze, learn, conclude and solve problems.
 
The systems which use this type of intelligence are known as artificial intelligent systems and their intelligence is referred to as artificial intelligence.

·         In AI, the main idea is to make the computer think like human beings, so that it can be then said that computers also have common sense.

·         Artificial Intelligence can be classified into various branches like Natural Language Processing (NLP), Speech Recognition, Automated Programming, Machine Learning, Pattern Recognition and Probabilistic Networks.

·         Artificial Intelligence is used in many areas such as problem solving, knowledge representation, learning, perception, social intelligence, gaming etc.

Artificial Intelligence and Neural Networks
Both are interconnected fields. Artificial Intelligence is the science and technology based on various functions to develop a system that can think and work like a human being. Neural networks are a systems designed based on the way human neurons work – to process data and learn from it. The more examples, the more the experience and thus more capability to solve future problems on its own.

·         Artificial intelligence is a field of science and technology based on “this site”disciplines such as computer science, biology, psychology, linguistics, mathematics and engineering.

·         The goal of AI is to develop computers that can simulate the ability to think, see, hear, walk, talk and feel.

·         In other words, simulation of computer functions normally associated with human intelligence, such as reasoning, learning and problem solving.

·         AI can be grouped under three major areas: cognitive science, robotics and natural interfaces.

·         Fussy logic systems can process data that are incomplete or ambiguous. Thus, they can solve semi-structured problems with incomplete knowledge by developing approximate inferences and answers, as humans do.

An Artificial Neural Network, often just called a neural network, is a mathematical model inspired by biological neural networks.

·         A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation.

·         In most cases a neural network is an adaptive system that changes its structure during a learning phase. Neural networks are used to model complex relationships between inputs and outputs or to find patterns in data.

·         Neural network software can learn by processing sample problems and their solutions. As neural nets start to recognize patterns, they can begin to program themselves to solve such problems on their own.
·         Neural networks are computing systems modelled after the human brain’s mesh like network of interconnected processing elements, called neurons. The human brain is estimated to have over 100 billion neuron brain cells. The neural networks are lot simpler in architecture. Like the brain, the interconnected processors in a neural network operate in parallel and interact dynamically with each other.

·         This enables the network to operate and learn from the data it processes, similar to the human brain. That is, it learns to recognize patterns and relationships in the data.

·         The more data examples it receives as input, the better it can learn to duplicate the results of the examples it processes. Thus, the neural networks will change the strengths of the interconnections between the processing elements in response to changing patterns in the data it receives and results that occur.

For example, neural network can be trained to learn which credit characteristics result in good or bad loans. The neural network would continue to be trained until it demonstrated a high degree of accuracy in correctly duplicating the results of recent cases. At that point it would be trained enough to begin making credit evaluations of its own.

Genetic algorithm software uses Darwinian (survival of the fittest), randomizing and other mathematics functions to simulate evolutionary processes that can generate increasingly better solutions to problems.