Appropriate problems for ann learning , Computer Engineering

Appropriate Problems for ANN learning - artificial intelligence- 

As we did for decision trees, it is essential to know when ANNs are the correct representation scheme for the task. The following are some characteristics of learning tasks for which artificial neural networks are a suitable representation:

1.   The concept (target function) to be learned may be characterized in terms of a real-valued function. There is some translation from the training examples to a set of real numbers and the output from the function is real-valued or (if a categorization) may be mapped to a set of real values. It is essential to remember that ANNs are only giant mathematical functions, so the data they play around with are numbers, rather than logical expressions, etc. it can sound restricted, but several learning problems may be expressed in a way that ANNs can deal with them, especially as real numbers contain Booleans (true and false mapped to +1 and -1), integers, and vectors of these data types may also be used.

2. Long training times are acceptable. Generally neural networks take a longer time to train

Then,  for instance, decision trees. Various factors, including the number of training examples, the value selected for the learning rate and the architecture of the network, have an effect on the time required to train a network. Training times may be varying from a few minutes to many hours.

3. It is not vitally essential that humans be able to understand accurately how the learned network carries out categorizations. As we look above, ANNs are black boxes and it is hard for us to get a handle on what its calculations are doing.

4. When using for the definite purpose it was learned for, the evaluation of the target

function needs to be fast. While it can take a long time to learn a network to, for example, decide whether a vehicle is a bus, car or tank, once the ANN has been learned, by using it for the categorization task is usually very fast. This can be very essential: if the network was to be used in a clash situation, then a quick decision regarding whether the object moving hurriedly towards it is a bus, tank, car or old lady could be vital.

In addition, in the training data neural network learning is quite robust to errors, because it is not trying to learn exact rules for job, but rather to minimize an error function.

Posted Date: 10/2/2012 6:42:21 AM | Location : United States

Related Discussions:- Appropriate problems for ann learning , Assignment Help, Ask Question on Appropriate problems for ann learning , Get Answer, Expert's Help, Appropriate problems for ann learning Discussions

Write discussion on Appropriate problems for ann learning
Your posts are moderated
Related Questions
Like ULINE the statement VLINE is used to insert vertical lines. No , Vline is not used to insert vertical lines.

Blocking and Non-Blocking network In non-blocking networks the route from any free input node to any free output node can always be offered. Crossbar is an best example of non-

On the Moodle site just below the assignment you will find data from a slow sine sweep test conducted on a car on a "four-post" road simulator for the frequency range 0 to 20 Hz in

Programmable read only memory (PROM) A PROM is a memory chip on which data can be written only one time. Once a program has been written onto a PROM, it's permanent. Unlike RAM

The next type of input is a Pull Down List. With this type you have to employ in place of and it also has a closing tag. This control is used when we have a

Q. Show a string in assembly language? MOV AH, 09H MOV DX, OFFSET   BUFF INT    21H Here data in input buffer stored in data segment is intended to be displayed on mo

Q. Describe about Frameset? Now make a master page in which you write below code. My Frame Page -- The Master Page

S oftware Engineering - Layered Technology Although various authors have developed personal definitions of software engineering, a definition given by Fritz Bauer at the semin

Explain the Design reusability of Verilog There is no concept of packages in Verilog. Functions and procedures used within a model should be  defined  in  the  module.  To  mak

Types E-commerce generally based on advertising, selling, marketing and buying, but due to the differences in needs, e-commerce has been classified according to the parties of the