20-04-2012, 01:59 PM
Artificial Neural networks:
electricl.doc (Size: 2.91 MB / Downloads: 117)
Designing and implementing intelligent systems has become a crucial factor for the innovation and development of better products for society. Such is the case of the implementation of artificial life as well as giving solution to interrogatives that linear systems are not able resolve.
An artificial neural network is a system based on the operation of biological neural networks, in other words, is using approach of biological neural system. A neural network is a parallel system, capable of resolving methods that linear computing cannot. (eg of Ann pattern recognition, prediction, system identification and controller.)Consider an image processing task such as recognizing an everyday object projected against a background of other objects. This is a task that even a small child's brain can solve in a few tenths of a second. But building a conventional serial machine to perform as well is incredibly complex. However, that same child might NOT be capable of calculating 2+2=4, while the serial machine solves it in a few nanoseconds.
Advantages:
• A neural network can perform tasks that a linear program can not.
• When an element of the neural network fails, it can continue without any problem by their parallel nature.
• A neural network learns and does not need to be reprogrammed.
• It can be implemented in any application.
• It can be implemented without any problem.
Disadvantages:
• The neural network needs training to operate.
• The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated.
• Requires high processing time for large neural networks.
Another aspect of the artificial neural networks is that there are different architectures, which consequently requires different types of algorithms, but despite to be an apparently complex system, a neural network is relatively simple.
In the world of engineering, neural networks have two main functions: Pattern classifiers and as non linear adaptive filters. As its biological predecessor,(mimics neurons) an artificial neural network is an adaptive system. By adaptive, it means that each parameter is changed during its operation and it is deployed for solving the problem in matter. This is called the training phase.
A artificial neural network is developed with a systematic step-by-step procedure which optimizes a criteria commonly known as the learning rule. The input/output training data is fundamental for these networks as it conveys the information which is necessary to discover the optimal operating point. In addition, a non linear nature makes neural network processing elements a very flexible system.
The Mathematical Model
For an artificial neuron, the weight is a number, and represents the synapse. A negative weight reflects an inhibitory connection, while positive values designate excitatory connections. The following components of the model represent the actual activity of the neuron cell. All inputs are summed altogether and modified by the weights. This activity is referred as a linear combination. Finally, an activation function controls the amplitude of the output.
The learning of weights is generally done as follows:
1- Set random numbers. For all weights.
2- Select a random input vector ej.
3- Calculate the output vector Oj with the current weights.
4- Compare Oj with the destination vector aj , if Cj = aj then continue with (2).
Else correct the weights according to a suitable correction formula and then continue with (2).
There are three type of learning in which the weights organize themselves according to the task to be learnt, these types are:-
U1- Supervised learning:-
The supervised is that, at every step the system is informed about the exact output vector. The weights are changed according to a formula (e.g. the delta-rule), if o/p is unequal to a. This method can be compared to learning under a teacher, who knows the contents to be learned and regulates them accordingly in the learning procedure.
electricl.doc (Size: 2.91 MB / Downloads: 117)
Designing and implementing intelligent systems has become a crucial factor for the innovation and development of better products for society. Such is the case of the implementation of artificial life as well as giving solution to interrogatives that linear systems are not able resolve.
An artificial neural network is a system based on the operation of biological neural networks, in other words, is using approach of biological neural system. A neural network is a parallel system, capable of resolving methods that linear computing cannot. (eg of Ann pattern recognition, prediction, system identification and controller.)Consider an image processing task such as recognizing an everyday object projected against a background of other objects. This is a task that even a small child's brain can solve in a few tenths of a second. But building a conventional serial machine to perform as well is incredibly complex. However, that same child might NOT be capable of calculating 2+2=4, while the serial machine solves it in a few nanoseconds.
Advantages:
• A neural network can perform tasks that a linear program can not.
• When an element of the neural network fails, it can continue without any problem by their parallel nature.
• A neural network learns and does not need to be reprogrammed.
• It can be implemented in any application.
• It can be implemented without any problem.
Disadvantages:
• The neural network needs training to operate.
• The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated.
• Requires high processing time for large neural networks.
Another aspect of the artificial neural networks is that there are different architectures, which consequently requires different types of algorithms, but despite to be an apparently complex system, a neural network is relatively simple.
In the world of engineering, neural networks have two main functions: Pattern classifiers and as non linear adaptive filters. As its biological predecessor,(mimics neurons) an artificial neural network is an adaptive system. By adaptive, it means that each parameter is changed during its operation and it is deployed for solving the problem in matter. This is called the training phase.
A artificial neural network is developed with a systematic step-by-step procedure which optimizes a criteria commonly known as the learning rule. The input/output training data is fundamental for these networks as it conveys the information which is necessary to discover the optimal operating point. In addition, a non linear nature makes neural network processing elements a very flexible system.
The Mathematical Model
For an artificial neuron, the weight is a number, and represents the synapse. A negative weight reflects an inhibitory connection, while positive values designate excitatory connections. The following components of the model represent the actual activity of the neuron cell. All inputs are summed altogether and modified by the weights. This activity is referred as a linear combination. Finally, an activation function controls the amplitude of the output.
The learning of weights is generally done as follows:
1- Set random numbers. For all weights.
2- Select a random input vector ej.
3- Calculate the output vector Oj with the current weights.
4- Compare Oj with the destination vector aj , if Cj = aj then continue with (2).
Else correct the weights according to a suitable correction formula and then continue with (2).
There are three type of learning in which the weights organize themselves according to the task to be learnt, these types are:-
U1- Supervised learning:-
The supervised is that, at every step the system is informed about the exact output vector. The weights are changed according to a formula (e.g. the delta-rule), if o/p is unequal to a. This method can be compared to learning under a teacher, who knows the contents to be learned and regulates them accordingly in the learning procedure.