2
$\begingroup$

In my country Expert System class is mandatory class if you want to take AI specialization in most universities. In class I learned how to make a rule base system, forward chaining, backward chaining, Prolog, etc. I enjoyed the class until I read a few comments in Stackoverflow that Expert System is no longer included in the AI field, some top university have stopped teaching that again.

I found the old screenshot one of the comments: enter image description here

Is that true? why? And from industrial view, with the rise of machine learning, is the expert system still in use today?

$\endgroup$
3
$\begingroup$

It's correct that knowledge based Expert systems have fallen out of fashion. They were intensive researched in the 1970s and 1980s. The new, more exciting topic, is called data-driven and machine learning approach. This kind of turnaround can be traced back in the literature. Since the 1990s lots of papers were created about data-mining and only a few literature was written about classical handcrafted expert systems.

Are expert system still in use?

The dinosaur from the 1980s was CLIPS. The sourcecode is available in the internet and a new Java version was programmed called Jess, but in general it is no longer a topic in the literature. Instead of focus on expert systems, many researchers have selected semantic web and OWL as their new home base. Some extensions in the OWL syntax have to do with creating rules similar to what was researched in the 1980s under the term expert system.

The shared similarity between expert systems and machine learning is, that both are transfering input into output signals in a control systems. A plant has input values which are measured by sensors and it has also output signals which are valves. The aim of the system in-between is to realize a certain policy. Expert systems are doing so with symbolic stored knowledge, while machine learning is using statistical patterns for the signal mapping.

According to the given literature and the amount of failed automation projects in the past, it can be sure, that the experts doesn't know how to realize the policy in optimal way. In the 1970s and 80s, expert systems were used, and later the machine learning concept. With both it is possible to store domain-knowledge in a machine readable way and perhaps the ideal plant control would be a hybrid of both.

$\endgroup$
  • 1
    $\begingroup$ I think this answer would be more complete if it gave relative strengths and weaknesses of expert systems vs ML, or gave examples of where expert systems are still employed today. Or both. $\endgroup$ – Neil Slater Feb 3 at 19:32
  • $\begingroup$ You argue against a simple overview of expert systems? Perhaps you're right. The answer is missing indeed a comparison to machine learning, and some examples for practical usage projects would also be helpful. I'm open to recommendations, the answer isn't carved in stone. $\endgroup$ – Manuel Rodriguez Feb 3 at 19:43
  • $\begingroup$ The OP's question is specifically about current relevance of Expert Systems. The overview is useful context, but I think a good answer would say more than they "have fallen out of fashion". Unfortunately my knowledge is mostly restricted to the modern NNs, but I believe first that expert systems still have important places in industry, I'd prefer see an expert system - with well understood behaviour - help manage a power plant instead of a neural net for instance. $\endgroup$ – Neil Slater Feb 3 at 19:49
  • $\begingroup$ I also think that better AI will be achieved in future through combining ideas from "classic AI" of formal logic and knowledgebase ontologies. However, I am afraid I cannot offer more than encouragement and wild guesses when it comes to facts about expert systems, so I cannot contribute much positive to the answer $\endgroup$ – Neil Slater Feb 3 at 19:50
  • $\begingroup$ @ManuelRodriguez your answer is so insightful! your answer and Neil Slater's comment about machine learning vs expert system are easy to understand. Thank you! and how about at University? is it true that expert system is no longer taught? $\endgroup$ – malioboro Feb 4 at 8:23
2
$\begingroup$

I would say Expert Systems is still being taught. For instance, if you look at some of the open courses like MIT's, there are still lectures on it.

Also, looking at the CLIPS documentation, you will find a couple of examples of usage from 2005.

What I suspect is that Expert Systems are now embedded with "normal systems" in practice. Hence it may be difficult to distinguish from systems used on a daily basis for diagnostics, etc. and not as popular as before.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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