Tek-Tips is the largest IT community on the Internet today!
Members share and learn making Tek-Tips Forums the best source of peer-reviewed technical information on the Internet!
-
Congratulations strongm on being selected by the Tek-Tips community for having the most helpful posts in the forums last week. Way to Go!
Learning algorithms
- Thread starter idinkin
- Start date
Algorithms are the coded solution of a specific problem.
In fact you could say a program itself is an algorithm
consisting of a multitude of other algorithms.
Algorithms you need not learn. They already exist and you
can use them.
So what you mean I think is how you can work on a specific
problem and create an algorithm.
But there's no general guideline for this.
There are different ways of sorting data, of retrieving data
from a file, of writing data to a file a.s.o.
The way they work depends on what YOU want them to do.
The algorithm should be on paper first, then you will do the
coding.
In fact you could say a program itself is an algorithm
consisting of a multitude of other algorithms.
Algorithms you need not learn. They already exist and you
can use them.
So what you mean I think is how you can work on a specific
problem and create an algorithm.
But there's no general guideline for this.
There are different ways of sorting data, of retrieving data
from a file, of writing data to a file a.s.o.
The way they work depends on what YOU want them to do.
The algorithm should be on paper first, then you will do the
coding.
- Thread starter
- #4
Search for Neural Network on the web.
for example go to:
Here is a couple of links that might me useful:
for example go to:
Here is a couple of links that might me useful:
I agree, the neural network is the best place to start. In particular, start out by learning a simple backpropagation neural network. You can search for "neural network backprop OR backpropagation code"
Don't get ahead of yourself until you master the basic backprop algorithm. There are a lot of variations using optimized parameter estimation methods, but that's all icing on the cake. Get used to the basic terminology and data structures of neural networks and you will go far.
Don't get ahead of yourself until you master the basic backprop algorithm. There are a lot of variations using optimized parameter estimation methods, but that's all icing on the cake. Get used to the basic terminology and data structures of neural networks and you will go far.
You may want to purchase "The Art of Computer Programming" by Donald E. Knuth (Get the latest version.) It is a three volume set that discusses all kinds of different algorithms (albeit in a mathematical form.) This is the de facto trilogy on alogrithms in general.
Hope this helps! Happy coding
*~-> EOR Candy <-~*
Hope this helps! Happy coding
*~-> EOR Candy <-~*
- Status
Similar threads
- Locked
- Question