Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

regarding neural networks

Status
Not open for further replies.

sreesri_avvaru

Newbie level 2
Joined
Feb 24, 2008
Messages
2
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,298
hi all,
im doing project on neural networks,but i have some doubts in it.if u know please help me.

1.what is the use of neural nets.Im solving constraint problem using neural net,but i got one doubt here why we are taking neural nets to solve this type of problems.computer also can do the same by executing the program.then what the need of it.Is there any particular reason?

2.while designing neral nets,how the neurons and weights are to be chosen?
 

sundarmeenakshi

Full Member level 3
Joined
Dec 12, 2006
Messages
188
Helped
19
Reputation
38
Reaction score
2
Trophy points
1,298
Activity points
2,258
sreesri_avvaru said:
hi all,
im doing project on neural networks,but i have some doubts in it.if u know please help me.

1.what is the use of neural nets.Im solving constraint problem using neural net,but i got one doubt here why we are taking neural nets to solve this type of problems.computer also can do the same by executing the program.then what the need of it.Is there any particular reason?

2.while designing neral nets,how the neurons and weights are to be chosen?
new net work is used for mking decision based on the importance of the operation
 

kiprono

Advanced Member level 4
Joined
Nov 18, 2005
Messages
114
Helped
19
Reputation
38
Reaction score
4
Trophy points
1,298
Location
Nairobi
Activity points
1,838
Neural nets have the ability to learn. they are useful if u have some training data to use for training. once trained it will be able to give u results based on a new set of inputs.
The type of neural net, number of neurons and weights are chosen based on the complexity of the system.
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Top