What is Back propagation in Neural Networks?

Answer Posted / rasmi ranjan das

A back-propagation neural network is only practical in
certain situations. Following are some guidelines on when
you should use another approach:

Can you write down a flow chart or a formula that
accurately describes the problem? If so, then stick with a
traditional programming method.
Is there a simple piece of hardware or software that
already does what you want? If so, then the development
time for a NN might not be worth it.
Do you want the functionality to "evolve" in a direction
that is not pre-defined? If so, then consider using a
Genetic Algorithm (that's another topic!).
Do you have an easy way to generate a significant number of
input/output examples of the desired behavior? If not, then
you won't be able to train your NN to do anything.
Is the problem is very "discrete"? Can the correct answer
can be found in a look-up table of reasonable size? A look-
up table is much simpler and more accurate.
Are precise numeric output values required? NN's are not
good at giving precise numeric answers.
Conversely, here are some situations where a BP NN might be
a good idea:

A large amount of input/output data is available, but
you're not sure how to relate it to the output.
The problem appears to have overwhelming complexity, but
there is clearly a solution.
It is easy to create a number of examples of the correct
behavior.
The solution to the problem may change over time, within
the bounds of the given input and output parameters (i.e.,
today 2+2=4, but in the future we may find that 2+2=3.8).
Outputs can be "fuzzy", or non-numeric.

Is This Answer Correct ?    6 Yes 4 No



Post New Answer       View All Answers


Please Help Members By Posting Answers For Below Questions

What is the uniform cost search algorithm?

606


What are the disadvantages of depth-first search algorithm?

570


Explain the Canny's Algorithm.

599


Consider the following algorithm, where the array A is indexed 1 through n: int add_them ( int n , int A[ ] ) { index i , j , k ; j = 0 ; for ( i = 1 ; i <= n ; i++) j = j + A[i] ; k = 1 ; for ( i = 1 ; i <= n ; i++) k = k + k ; return j + k ; } (a) If n = 5 and the array A contains 2, 5, 3, 7, and 8, what is returned? (b) What is the time complexity T(n) of the algorithm?

1863


can anyone help me with some suggestions and improvemnts for sage line 50?

2129






Which search algorithm will use a limited amount of memory in online search?

744


Tell us how will you know which machine learning algorithm to choose for your classification problem?

505


What is local search algorithms?

593


What is the depth-first search algorithm?

596


List the different algorithm techniques in machine learning?

522


What is the iterative deepening depth-first search algorithm?

559


Give a general algorithm for converting a m-array tree to a 2-ary tree.

625


Tell briefly about the Banker's algorithm and what is it used for?

576


What is software cycle? Give a diagrammatic representation?

520


what is software cycle?give a diagramatic representation

2408