1
$\begingroup$

I'm currently doing some reading into AI and up to this point couldn't find a satisfying answer to this question: what's the difference between a rule based system and an artificial neural network?

From my understanding both are trying to do inference based on a variety of different inputs.

$\endgroup$
1
  • 2
    $\begingroup$ The difference is not what they are trying to do but how they do it. $\endgroup$ Oct 9, 2012 at 10:07

2 Answers 2

4
$\begingroup$

The difference is vast, although as Dave wrote, the resulting black box might look the same from outside. Rule-based systems are examples of "old style" AI, which uses rules prepared by humans. Neural networks are examples of "new style" AI, whose mechanism is "learned" by the computer using sophisticated algorithms, and as a result, we humans don't really understand why it works. While in some cases rule-based systems could be effective, the general trend in AI has been to switch to machine-learning algorithms such as neural networks, due to their much better performance.

$\endgroup$
1
$\begingroup$

Just to give a slightly more general perspective than the other answers: "trying to do inference based on a variety of different inputs" is basically what much of the field is doing and it is a very general problem.

The idea is that you are looking for some simple, general way to explain how data observations are associated. This "explanation" is called the model. Of course there is an infinite number of types of models that you could check, and the "true" model underlying your data could be incredibly complex (for example, consider modelling the behavior of a live organism from its molecular components). From this you can see why the main challenge is to find efficient algorithms to identify different kinds of good predictive models.

Rule-based systems and Artificial Neural Networks are just some of the different algorithms/models that are being used. Other popular approaches are Support Vector Machines, decision trees, ensemble methods, probabilistic graphical models, and there are many others.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.