Neural networks have a large appeal to many researchers due to their great closeness to the structure of the brain, a characteristic not shared by more traditional systems.In analogy to the brain, an entity is made up of interconnected neurons. Neural networks are made up of interconnected processing elements called units, which respond in parallel to a set of input signals to each. The unit is the relevant of its brain counterpart, the neuron.A neural performs in two different modes: learning (or training) and testing. During learning, a set of examples is presented to the network. At the beginning of the training process, the network “guesses” the output for each example. However, as training goes on, the network modifies internally until it reaches a stable stage at which the outputs are considered satisfactory. Learning is simply an adaptive process during which the weights associated with all the interconnected neuron change in order to provide the best possible response to all the observed stimuli. Neural networks can learn in two ways, supervised or unsupervised. In both the cases, once the network has reached the desired performance, the learning stage is over and the associated weights are frozen. The final stage of the network is preserved and it can be used to classify new, previously unseen inputs. At the testing stage, the network receives an input signal and processes it to produce an output. If the network has correctly learnt, it should be able to generalize, and the actual output produced by the network should be almost as good as the ones produced in the learning stage for similar inputs.In making determinations, neural networks use several principles; including gradient based training, fuzzy logic, genetic algorithms and Bayesian methods.
Neural networks are particularly effective for predicting events when the networks have a large database of prior examples to draw on. Strictly speaking, a neural network implies a non digital computer but neural networks can be simulated on digital computers. There is a vast implementation of neural networks in almost every field.
One of the original aims of neural network is to understand and shape the functional characteristics and computational properties of the brain when it performs the cognitive processes such as sensorial perception, concept categorization, concept association and learning. However, today a great deal of effort is focused on the development of neural networks for applications such as pattern recognition and classification, data compression, optimization.
The advantage of neural networks over conventional programming lies on their ability to solve problems that do not have an algorithmic solution or the available solution is too complex to be found. Neural networks are always suited to tackle problems that people are good at solving, like prediction and pattern recognition. Neural networks have been applied within the medical domain for clinical diagnosis, image analysis and interpretation, signal analysis and interpretation and drug development.
Neural networks have found a wide range of applications, the majority of which are associated with problems in pattern recognition and control theory. Here I give u a small selection of examples, focusing on applications in routine use.The problem of recognizing handwritten characters is a challenging one that has been widely studied as a prototypical example of pattern recognition. Some of the most successful approaches to this problem are based on neural network techniques and have resulted in several commercial applications. Mass screening of medical images is another area in which neural networks have been widely explored, where they form the basis for one of the leading systems for semi-automatic interpretation of cervical smears. As a third example of pattern recognition we mention the problem of verifying handwritten signatures, based on the dynamics of the signature captured during the signing process, where the leading approach to this problem is again based on neural networks.
The prospects for neural networks seem excellent, given the increasing sophistication of the underlying theory, the increasing range of applicability of the techniques, and the growing scale of the applications that are being undertaken. The interdisciplinary nature of research in the field seems certain to persist and to bring new vigor into allied fields. Finally, future progress in theoretical neuroscience will provide a continuing impetus for the development and understanding of network models of intelligence.
Email: zamilhussain2@gmail.com
