Jump to content

Talk:Computational intelligence

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

Article

[edit]

Seems like this article had some disagreements coming in over the weekend. This involves the extent and breakdown of the topic. A quick link check produced the following:

  • Bioinformatics or computational biology is about the sovling of biological problems
  • Bioengineering deals with bio-molecular and molecular processes, and includes biomedical- food- and agricultural engineering
  • Autonomous mental development is the investigating of evolution through computer programs
  • Computational finance is a form of finance which relies on mathematical methods
  • Computational economics is the branch of applied mathematics concerned with the financial markets
  • Intelligent Systems is a video game developer team of Nintendo Co., Ltd.
  • Emergence is the process of complex pattern formation from simpler rules (occurring over time or over disparate size scales)
  • Data mining is the extraction of implicit, previously unknown, and potentially useful information from data, used with a varied meaning

These topics are not subsets of CI, although they might be related. Machine learning and Expert systems should be removed from 'related topics' as is explained at the end of the first article paragraph. Lets keep the disagreements to the discussion. --moxon 17:43, 31 October 2005 (UTC)[reply]


Neural Nets

[edit]

I don't think this is entirely accurate. The article states that ANNs are closely *related* to ML. They're not just closely related, they are common algorithms used for ML. This article gives the false impression that ANNs are actually separate. I certainly understand why ANNs are listed under CI, but that shouldn't make it exclusive, especially since ANNs have been so common in ML for so long. —Preceding unsigned comment added by Jmacglashan (talkcontribs) 07:09, 15 November 2008 (UTC)[reply]

To some extent. Neural nets are rather out of favor in mainstream statistical machine learning these days; even the conference that has them in its name, NIPS, does not publish many neural-net papers these days. They were popular in ML in the 1980s and early 1990s, but have mostly fallen out of favor after the rise of more influence from statistics. In particular, the common backpropagation algorithm for ANNs is, seen from a statistical perspective, just gradient descent on a particular class of functions, and so statistical ML people see no strong reason to prefer this particular gradient-descent-trained predictor to all other predictive models. --Delirium (talk) 03:42, 7 March 2009 (UTC)[reply]

Contradiction, confusion

[edit]

I don't get it: First ci "either rejects fuzzy systems or ignores neural networks", then both are listed as part of ci. ??? And more generally, saying what the two sides (ci and ml) reject is not a clear way to explain what they are. This ci beginner needs help. Thx, "alyosha" 03:01, 20 December 2005 (UTC)[reply]

I edited it to try and solve the disambiguation: fuzzy rejects and neurals ignores stats. The deffinition of CI and ML is quite fuzzy, at the moment I think examples and differences are the simplest way to define then. They are 2 different classical approached to AI. ML builds heavily on statistics, CI does not. This is the most obvious difference. A rough definition might be "learning from empirical data". --moxon 15:27, 20 December 2005 (UTC)[reply]

Merge?

[edit]

Do we really need a seperate article for a specific arbitrary, mechanical distinction on ways to achieve weak AI? How about this article gets redirected to a new article on the computational aproaches to AI? - Jake11...

Strong/Weak AI is a philosophical issue or matter of opinion and has no impact on the techniques followed. CI denotes distinct methods opposing conventional/neat AI. See the IEEE CI Soc. as referenced. This is an existing and growing branch of computer science & engineering and needs no redirection. --moxon 16:27, 16 March 2006 (UTC)[reply]

Not alternative to AI, etc.

[edit]

Computational intelligence is a subset of AI. It is an alternative to GOFAI and the 'neats'. In addition Evolutionary computation is not equal to Genetic algorithms and Fuzzy logic is not an algorithm. --moxon 10:19, 16 January 2007 (UTC)[reply]

Is CI a subfield of AI?

[edit]
The answer is: the question is controversial.
It comes down to the sources. Here is a survey of the sources given for this article:
This is not how it is used in the article's first reference: (Poole et al. 1998). They say: "Artificial Intelligence is the established name for the field we have defined has Computation Intelligence" on page 1. So they think of it as new name for the old field.
The standard AI textbook Artificial Intelligence: A Modern Approach doesn't seem to mention computational intelligence at all. We could assume that they don't think that the distinction made in the article is interesting enough to merit discussion.
Reading the IEEE CIS web site seems to support CI as a subfield, but only if one reads between the lines: knowledge based systems, for example, is missing from the list, as is logic programming.
The Computational Intelligence Group from Amsterdam sees CI a new subfied. So there's that.
The journal Computation Intelligence's description reads "This leading international journal promotes and stimulates research in the field of artificial intelligence (AI)." So this journal description explicitly does not recognize CI as a subfield.
The ://www.waset.org/ijci/ International Journal of Computational Intelligence] lists the same areas as this article, and as before, logic programming, expert systems and knowledge based systems are all missing. So this would seem to support the idea of CI as subfield, but again, this is a supposition after the fact.
The ://www.waset.org/ijis/ Journal of Intelligence Technology] doesn't seem to be aware of computational intelligence; it shouldn't be connected to this article at all.
The International Journal of Computational Intelligence Research treats CI as a subfield. So there's also that.
And finally, CIRG (which has the nicest website) gives it's definition in complete line with the idea of this as subfield.
So the answer (for Wikipedia) must be: the subject is controversial, and this article should take a neutral point of view. There seems to be (at least) two uses of the term. (1) as a new name for AI as it is practiced today, in contrast to the old (and failed) ways of doing AI. (2) as a new sub-field of AI, gathering together some approaches and ignoring others. The article should mention that different researchers, journals and research groups use the word differently.
I assume this article is about creating a named reference for a concept that should subsume artificial intelligence. All referenced elements (methods and theories) are somehow a subset of artificial intelligence. In my opinion the concept of computational intelligence is somehow the chain or orchestrated network of methods to achieve a computed objective in the broader sense. ---- User:Neum.dan
As an editorial choice, I would not expand this article beyond making this point, since any additional material should be covered in the article on AI, since many people still consider this material as part of AI. (Unfortunately, the article on AI does need a lot of tuning up). ---- CharlesGillingham 03:28, 5 September 2007 (UTC)[reply]

I would add a third use of the term: (3) a synonym for AI. I'd say that Computational Intelligence uses CI in such a way.

Regards, --zeno 11:48, 3 October 2007 (UTC)[reply]

Where is the "Controversy" Section then?

[edit]

CI is clearly not well defined. To sum up (may be somewhat abusively), CI can be taken for a synonym of AI, or as a subfield of AI.

Why not start by explaining that --explicitly giving some pointers showing both viewpoints-- before continuing with the "subfield" view?

Another option is to write a "Controversy" section but I am not sure this is worth it.

Regards, --[unregistered user] 19 August, 2011 (UTC)


Is CI "scuffy" or "neat"?

[edit]

Answer: It can be either.

First a source: Russell & Norvig, describing modern approaches to AI, write "recent years have seen a revolution in the content and the methodology of work in AI" and "some have characterized this change as a victory of the 'neats'" and later that "neural networks also fit into this trend." They are implicitly saying: neural networks are neat.

The precise mathematics used in genetic algorithms and neural networks can be very 'neat'. And these are clearly in CI's area.

Also, the sloppy, ad hoc symbolic AI epitomized by Doug Lenat's Cyc is 'scruffy', but it's good old fashioned symbolic AI, and is not in CI's area.

The neat/scruffy distinction is orthogonal to the GOFAI/CI distinction: there are cases of neat GOFAI (logic programming), scruffy GOFAI (semantic webs), neat CI (pattern matching neural networks), and scruffy CI.

If there are sources that disagree with this analysis, I'd love to see them. ---- CharlesGillingham 03:28, 5 September 2007 (UTC)[reply]

The GOFAI/CI distinction isn't quite the AI/CI distinction though, since AI includes non-GOFAI stuff; in fact statistical AI is probably bigger than GOFAI these days, judging by the proceedings of recent AAAI conferences and the growth of non-symbolic-heavy AI venues like ICML. CI is more of a competitor to that line of work, coming from an engineering direction (IEEE is a major sponsor), and with more of an emphasis on techniques like neural nets and GAs that are no longer particularly current in statistical AI. --Delirium (talk) 03:47, 7 March 2009 (UTC)[reply]
I agree. See the previous. ---- CharlesGillingham (talk) 17:09, 23 October 2009 (UTC)[reply]

AI/CI

[edit]

Hi

If we were too take all CI topics and fields out of AI what would be left ? I am a little confused on that part.

Chaosdruid (talk) 22:04, 10 November 2010 (UTC)[reply]

I can answer that, although others may disagree; first note that the term "computational intelligence" is used in different ways by different people (see a few posts above). The way this article uses the term is this: CI uses "soft computing" tools, such as fuzzy logic, bayesian nets, optimization, genetic algorithms and neural networks. These tools are used to solve problems like pattern recognition and machine learning. CI does not, in general, work on problems like knowledge representation or theorem proving, which require "symbol manipulation" and detailed, hand coded semantic knowledge. For an example of AI that isn't CI, consider Cyc or expert systems ---- CharlesGillingham (talk) 09:24, 17 November 2010 (UTC)[reply]

Relation to artificial intelligence?

[edit]

I seems like this article is related to artificial intelligence, especially since it is included in the category artificial intelligence, as well as having a link to the artificial intelligence portal, but the body text doesn't mention artificial intelligence at all. The relation between the two topics needs to be made clear. —Kri (talk) 14:57, 25 February 2014 (UTC)[reply]

Probabilisitic Methods

[edit]

Fuzzy Logic is by definition not probabilistic. It is an degree of assignment to a specific concept, in the sense of e.g. property or truth, with partial truth. Probability is a chance of a specific outcome based on a repeatedly occuring events based on partial knowledge. — Preceding unsigned comment added by Neum.dan (talkcontribs) 12:29, 12 April 2018 (UTC)[reply]

Draft for updating the article

[edit]
  • in the talk page it was asked if computational intelligence can be merged with computational approaches of AI.
  • "Computational Intelligence" (CI) has 648k papers at google scholar but is seldom teached at university
  • teached in university at British columbia, Technical University of Dortmund (involved in the European fuzzy boom) and at Georgia Southern University
  • all courses have in common that Fuzzy logic takes a major role in it
  • university has not enough resources to teach an entire course on CI, instead it is put into a introduction lecture about AI [1]
  • CI is highly researched but seldom teached at the university [2]
  • interdisciplinary approach [3]
  • multidisciplinary education for understanding complex systems and adaptive systems in the context of STEM [4]
literature
  • [1] Zhang, Mengjie. "Experience of Teaching Computational Intelligence in an Undergraduate Level Course [Educational Forum]." IEEE Computational Intelligence Magazine 6.3 (2011): 57-59.
  • [2] Minaie, Afsaneh, et al. "Computational Intelligence Course in Undergraduate Computer Science and Engineering Curricula." age 23 (2013): 1.
  • [3] Venayagamoorthy, Ganesh K. Kumar. "A successful interdisciplinary course on coputational intelligence." IEEE Computational Intelligence Magazine 4.1 (2009): 14-23.
  • [4] Samanta, Biswanath. "Computational intelligence: a Tool for Multidisciplinary Education and Research." Proceedings of the 2011 ASEE Northeast Section Annual Conference, University of Hartford. 2011.--ManuelRodriguez (talk) 13:02, 13 March 2020 (UTC)[reply]