finger print
ARTIFICIAL NEURAL NETWORKS
INRODUCTION
Over the last 25 years artificial neural networks have found its way into various applications ranging from character recognition, pattern recognition, handwriting recognition and so many others. Artificial neural networks are models inspired by the animal central nervous system which includes the brain and that of many other organisms. Frequently neural networks is used in a broad sense which group together different families of algorithms and methods.
Artificial Neural Network is trained to solve certain challenges using sample data, in this way identically built ANN can be used to perform different task depending on the training received. Through proper training, ANN is capable of generalization, the ability to recognize similarities among different input patterns, especially patterns that have been corrupted by noise. The term Neural Network is used to describe different models of computation in a single neuron or whole area of the brain.
For instance, in a neural network for handwriting recognition, a set of input neurons may be activated by the pixel of an input image .the activation of these neurons are then handed on, weighted and transformed by some functions determined by the network designer to other neurons. Like other machine learning methods, ANN have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition.
HISTORICAL BACKGROUND OF ARTIFICIAL NEURAL NETWORKS
The history of neural network is traced back to the work of trying to model the neuron. The first model of a neuron was introduced by physiologists, McCulloch and Pitts in (1943) they created a computational model for neural networks based on the mathematical methods and algorithms. The model they created had two inputs and a single output.
McCulloch and Pitts notice that a neuron would not activate if only one of the inputs was in
INRODUCTION
Over the last 25 years artificial neural networks have found its way into various applications ranging from character recognition, pattern recognition, handwriting recognition and so many others. Artificial neural networks are models inspired by the animal central nervous system which includes the brain and that of many other organisms. Frequently neural networks is used in a broad sense which group together different families of algorithms and methods.
Artificial Neural Network is trained to solve certain challenges using sample data, in this way identically built ANN can be used to perform different task depending on the training received. Through proper training, ANN is capable of generalization, the ability to recognize similarities among different input patterns, especially patterns that have been corrupted by noise. The term Neural Network is used to describe different models of computation in a single neuron or whole area of the brain.
For instance, in a neural network for handwriting recognition, a set of input neurons may be activated by the pixel of an input image .the activation of these neurons are then handed on, weighted and transformed by some functions determined by the network designer to other neurons. Like other machine learning methods, ANN have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition.
HISTORICAL BACKGROUND OF ARTIFICIAL NEURAL NETWORKS
The history of neural network is traced back to the work of trying to model the neuron. The first model of a neuron was introduced by physiologists, McCulloch and Pitts in (1943) they created a computational model for neural networks based on the mathematical methods and algorithms. The model they created had two inputs and a single output.
McCulloch and Pitts notice that a neuron would not activate if only one of the inputs was in