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
1. Design a DTD for a new XML application called Library Markup Language (LibML) appropriate to capture the list of your items of collection . Put the DTD into a file named librar

Q. Demonstration of sorting problem? The term sorting implies organising elements of a provided set of elements in a specific order i.e. descending order / ascending order / al

What is a shift register? Can a shift register be used as a counter? If yes, explain how?     Ans: Shift Register: A register wherein data gets shifted towards left or right

Explain the violating basic security principles There are drawbacks to permitting users to access the Intranet as well as not permitting them. A simple consideration such as a

Texture Texture is how artists show what an object would feel like to touch. This can have a dramatic effect on how an image is perceived. Imagine for instance an image that h

What are the largest UDP messages that can fit into single Ethernet frame? UDP utilizes IP for delivery. As ICMP UDP packet is encapsulated in IP datagram. Therefore entire UDP

TARGET = "_blank" "_blank" opens new document in a new window. Run the code given in Figure and check how it works. This value doesn't require the use of any frames. "_blank"

Minimize the logic function F(A, B, C, D) = ∑ m(1,3,5,8,9,11,15) + d(2,13) using NAND gate with help of K-map. Ans. Realization of given expression by using NAND gates:  In

Q. Illustrate Character Coded Data? The input output happens in the form of ASCII data. These ASCII characters are entered as a string of data. For illustration to get two numb

Define port? Give types of port available? Ans: An I/O interface consists of circuitry needed to connect an I/O device to computer bus. One side consists of a data path contain