slugUsing Neural Networks in Medical Diagnosis Analysis Improvement
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2014, Vol 2, Issue 5
Abstract
The main objective of this research work is to improved Neural networks involve long training times, and are therefore more suitable for applications where this is feasible. They require a number of parameters which are typica lly best determined empirically, such as the network topology or “structure". Neural networks have been criticized for their poor interpretabilit y, since it is difficult for humans to interpret the symbolic meaning behind the learned weights. These feature s initially made neural networks less desirable for data mining. Advantages of neural networks, however, include their high tolerance to noisy data as well as their ability to classify patterns on which they have not been trained. In addition, several algo rithms have recently been developed for the extraction of rules from trained neural networks. These factors contribute towards the usefulness of neural networks for classification in data mining. The most popular neural network algorithm is the back propag ation algorithm, proposed in the 1980's. Back propagation learns by iteratively processing a set of training samples, comparing the network's prediction for each sample with the actual known class label. For each training sample, the weights are modified s o as to minimize the mean squared error between the network's prediction and the actual class. These modifications are made in the “backwards" direction, i.e., from the output layer, through each hidden layer down to the first hidden layer (hence the name back propagation). Although it is not guaranteed, in general the weights will eventually converge, and the learning process stops. Initialize the weights - The weights in the network are initialized to small random numbers (e.g., ranging from - 1.0 to 1.0 , or - 0.5 to 0.5). Each unit has a zero or more bias associated with it. The biases are similarly initialized to small random numbers. Each training sample, X, is then processed.
Authors and Affiliations
Niyati Shukla, Aparna Dubey, Dr. Vishnu Kumar Mishra
Keywords
Related Articles
- EP ID EP18049
- DOI -
- Views 322
- Downloads 13
Advancement in Material Science
Material science is a branch of science with a myriad of disciplines, which encompass the investigation and improvement of novel robust materials with the desired physical and chemical properties. Today material science...
A Novel Approach For Indian Currency Denomination Identification
it is very difficult to count different denomination notes in a bunch especially in banking. This paper proposes an image processing technique to extract paper currency denomination. The extracted ROI (Region of Interes...
slugAn Evolutionary Algorithm for Automated Test Data Generation for Software Programs
Software testing takes a considerable amount of time and resources spent on producing software it would be useful to have ways to reduce the cost of software testing so one of them is automatic test data generator- a sy...
Improving Trust on Recommendation models using the PCA Recommend based Iterative Analysis against the User trust and Item Rating
The recommendation modelling is challenging issue in the research of recommendation model by integrating the information source with sparsity and high dimensional structure against cold start and curse of dimensionality...
Analysis of Multicylinder Petrol Engine Intake Manifold Flow using CFD
Multicylinder engines are most widely used in high sector cars so as to get comfort. The power balancing of multicylinder engines are very high but the fuel efficiency is not in the expected range. This is due to the lo...