LIVE GST Certification Course by CA Arun Chhajer begins 27th April. Register Now!!

tell this

qarni (student) (1220 Points)

12 February 2008

can any one tell about NEURAL NETWORK?

Reply
Follow
Share

4 Replies

MOHIT MAHAJAN (LCS, ACA) (2050 Points)
Replied 12 February 2008

Here are couple of definitions searched from google: A type of statistical computer program which classifies large and complex data sets by grouping cases together in a way similar to the human brain. Used in data mining. In information technology, a neural network is a system of programs and data structures that approximates the operation of the human brain. A neural network usually involves a large number of processors operating in parallel, each with its own small sphere of knowledge and access to data in its local memory. Typically, a neural network is initially "trained" or fed large amounts of data and rules about data relationships (for example, "A grandfather is older than a person's father"). A program can then tell the network how to behave in response to an external stimulus (for example, to input from a computer user who is interacting with the network) or can initiate activity on its own (within the limits of its access to the external world).

qarni (student) (1220 Points)
Replied 12 February 2008

thanx

Mahidhar (28 Points)
Replied 13 February 2008

Neural Networks (NN) are also used as fraud detection programs. e.g. Consider a Bank. On of the function of bank is to provide loans. By creating a NN, the bank will feed its past data in the NN about the applicant, the loan details, the financial ratios and the outcome of the loan. The NN on a trial and error basis will try to establish a non linear relationship between the applicant financial ratios and the outcome of the loan and will create a model of the same. So the next time when a application for loan come the bank would simple process the application using the NN and try to predict the outcome of the loan. An NN is a type of nonlinear statistical analysis program that utilizes a learning process (trial and error) to repeatedly analyze a collection of historical data sets to recognize a pattern in that data and to automatically produce a model of that data.