Artificial neural networks, Computer Engineering

Artificial Neural Networks:

However imagine now in this example as the inputs to our function were arrays of pixels and there actually taken from photographs of vehicles such that the output of the function is either 1, 2 or 3 when 1 stands for a car and 2 stands for a bus and 3 also stands for a tank.

Hence in this case there the function that takes an array of integers representing pixel data and outputs either 1 or 2 or 3 will be fairly complicated then it's just doing the same kind of thing as the two simpler functions. 

Presumably the functions learned an example as categorise photos of vehicles into a category of car or bus or tank then are so complicated that we say the ANN approach is a black box approach is because of that the function performs well at its job so that we cannot look inside it to gain a knowledge of how it works. However this is a little unfair as maybe there are some projects that have addressed the problem of translating learned neural networks into human readable forms. Moreover,, there in generally ANNs are used in cases when the predictive accuracy is  of greater importance than understanding the learned concept.

Posted Date: 1/11/2013 6:47:51 AM | Location : United States







Related Discussions:- Artificial neural networks, Assignment Help, Ask Question on Artificial neural networks, Get Answer, Expert's Help, Artificial neural networks Discussions

Write discussion on Artificial neural networks
Your posts are moderated
Related Questions
What is swapping?   A process can be swapped out temporarily of memory to a backing store and after that brought back in memory for execution as continued.

What is the advantage of buffering? Is buffering always effective? Justify your answer with help of an example. I/O buffer: One type of input-output requirement arises from d

Q. Returns information about present virtual machine? int pvm_parent( void ) Returns the tid of process which spawned the calling process.  int pvm_tidtohost(


Companding helps in reducing with respect to signal:  (A) Interference                    (B) Signal overloading (C) Non linearity                 (D) Quantization noise

What is pipelining? It is a method of decomposing a sequential process into sub-operations, with each sub-process being implemented in a special dedicated segment that operates

Diffrentiate programming tools and authoring tools Distinction between programming tools and authoring tools is not at first obvious. Though, authoring tools require less techn

What is schedulers?  A process migrates between the various scheduling queues throughout its life time. The OS must select processes from these queues in some fashion. This sel

We have multiple instances in RTL (Register Transfer Language), do you do anything special during synthesis stage? Whereas writing RTL(Register Transfer language),say in Verilo