Editing Computational intelligence (section)

== Relationship between hard and soft computing and artificial and computational intelligence ==
Artificial intelligence (AI) is used in the media, but also by some of the scientists involved, as a kind of umbrella term for the various techniques associated with it or with CI.<ref name=":15" /><ref name=":11">{{Cite journal |last=Bezdek |first=James C. |date=April 2016 |title=(Computational) Intelligence: What's in a Name? |url=https://cis.ieee.org/images/files/Documents/history/2016_SMC_Mag_What_is_CI_optimised.pdf |journal=IEEE Systems, Man, and Cybernetics Magazine |volume=2 |issue=2 |pages=4–14 |doi=10.1109/MSMC.2016.2558778 |issn=2333-942X}}</ref> Craenen and Eiben state that attempts to define or at least describe CI can usually be assigned to one or more of the following groups:

* "Relative definition” comparing CI to AI
* Conceptual treatment of key notions and their roles in CI
* Listing of the (established) areas that belong to it<ref name=":13">{{Cite encyclopedia |last1=Craenen |first1=Bart |last2=Eiben |first2=A.E. |url=https://www.researchgate.net/publication/231557861 |title=Computational Intelligence |encyclopedia=Encyclopedia of Life Support Systems (EOLSS), vol. 4, Artificial Intelligence |publisher=Eolss Publishers. Developed under the Auspices of the UNESCO |year=2009 |editor-last=Joost |editor-first=N.K. |location=Oxford, UK |language=en |chapter=}}</ref>

[[File:Relationship AI-HC CI-SC.svg|thumb|259x259px|Relationship between hard computing and artificial intelligence on the one hand and soft computing and computational intelligence on the other.<ref name=":10" />]]The relationship between CI and AI has been a frequently discussed topic during the development of CI. While the above list implies that they are synonyms, the vast majority of AI/CI researchers working on the subject consider them to be distinct fields, where either<ref name=":13" /><ref name=":11" />

* CI is an alternative to AI
* AI includes CI
* CI includes AI

The view of the first of the above three points goes back to [[Lotfi A. Zadeh|Zadeh]], the founder of the fuzzy set theory, who differentiated machine intelligence into hard and [[soft computing]] techniques, which are used in artificial intelligence on the one hand and computational intelligence on the other.<ref>{{Cite journal |last=Zadeh |first=Lotfi A. |date=April 1994 |title=Fuzzy Logic, Neural Networks, and Soft Computing |journal=Communications of the ACM |language=en |volume=37 |issue=3 |pages=77–84 |doi=10.1145/175247.175255 |issn=0001-0782}}</ref><ref name=":17">{{Citation |last=Zadeh |first=Lotfi A. |title=Roles of Soft Computing and Fuzzy Logic in the Conception, Design and Deployment of Information/Intelligent Systems |date=1998 |work=Computational Intelligence: Soft Computing and Fuzzy-Neuro Integration with Applications |pages=1–9 |editor-last=Kaynak |editor-first=Okyay |place=Berlin, Heidelberg |publisher=Springer |language=en |doi=10.1007/978-3-642-58930-0_1 |isbn=978-3-642-63796-4 |editor2-last=Zadeh |editor2-first=Lotfi A. |editor3-last=Türkşen |editor3-first=Burhan |editor4-last=Rudas |editor4-first=Imre J.}}</ref> In hard computing (HC) and AI, inaccuracy and uncertainty are undesirable characteristics of a system, while soft computing (SC) and thus CI focus on dealing with these characteristics.<ref name=":6" /> The adjacent figure illustrates these relationships and lists the most important CI techniques.<ref name=":10" /> Another frequently mentioned distinguishing feature is the representation of information in symbolic form in AI and in sub-symbolic form in CI techniques.<ref name=":9" /><ref>{{Cite book |last1=Kruse |first1=Rudolf |title=Computational Intelligence: A Methodological Introduction |last2=Mostaghim |first2=Sanaz |last3=Borgelt |first3=Christian |last4=Braune |first4=Christian |last5=Steinbrecher |first5=Matthias |last6=Klawonn |first6=Frank |last7=Moewes |first7=Christian |date=2022 |publisher=Springer |isbn=978-3-030-42226-4 |edition=3rd |series=Texts in Computer Science |location=Cham, Switzerland |pages=8 |chapter=Introduction to Artificial Neural Networks}}</ref>

Hard computing is a conventional computing method based on the principles of certainty and accuracy and it is deterministic. It requires a precisely stated analytical model of the task to be processed and a prewritten program, i.e. a fixed set of instructions. The models used are based on [[Boolean algebra|Boolean logic]] (also called ''crisp logic<ref>{{Cite web |title=Fuzzy Sets and Pattern Recognition |url=http://www.cs.princeton.edu/courses/archive/fall07/cos436/HIDDEN/Knapp/fuzzy002.htm |access-date=2015-11-05 |website=www.cs.princeton.edu}}</ref>''), where e.g. an element can be either a member of a set or not and there is nothing in between. When applied to real-world tasks, systems based on HC result in specific control actions defined by a mathematical model or algorithm. If an unforeseen situation occurs that is not included in the model or algorithm used, the action will most likely fail.<ref name=":18">{{Cite web |date=2024-12-26 |title=Soft Computing vs. Hard Computing: Key Differences |url=https://wisdomplexus.com/blogs/soft-computing-vs-hard-computing/ |access-date=2025-02-07 |website=WisdomPlexus}}</ref><ref name=":19">{{Cite journal |last1=Sidda |first1=Sakunthala |last2=Kiranmayi |first2=R. |last3=Nagaraju Mandadi |first3=P. |date=2018-02-28 |title=Soft Computing Techniques and Applications in Electrical Drives Fuzzy logic, and Genetic Algorithm |url=https://www.researchgate.net/publication/322518823 |journal=HELIX |volume=8 |issue=2 |pages=3285–3289 |doi=10.29042/2018-3285-3289 |s2cid=57747778}}</ref><ref name=":20">{{Cite web |date=2024-06-19 |title=Soft Computing vs. Hard Computing |url=https://www.uopeople.edu/blog/soft-computing-vs-hard-computing/ |access-date=2025-02-07 |website=University of the People}}</ref><ref name=":21">{{Cite web |date=2022-10-11 |title=Soft Computing vs. Hard Computing: Understanding the Differences and Applications |url=https://computationalintelligence.net/soft-computing-vs-hard-computing-understanding-the-differences-and-applications/ |url-status= |access-date=2025-02-08 |website=CINET - Computational Intelligence Mastery}}</ref>

Soft computing, on the other hand, is based on the fact that the human mind is capable of storing information and processing it in a goal-oriented way, even if it is imprecise and lacks certainty.<ref name=":17" /> SC is based on the model of the human brain with probabilistic thinking, fuzzy logic and multi-valued logic. Soft computing can process a wealth of data and perform a large number of computations, which may not be exact, in parallel. For hard problems for which no satisfying exact solutions based on HC are available, SC methods can be applied successfully. SC methods are usually stochastic in nature i.e., they are a randomly defined processes that can be analyzed statistically but not with precision. Up to now, the results of some CI methods, such as deep learning, cannot be verified and it is also not clear what they are based on. This problem represents an important scientific issue for the future.<ref name=":18" /><ref name=":19" /><ref name=":20" /><ref name=":21" />

AI and CI are catchy terms,<ref name=":11" /> but they are also so similar that they can be confused. The meaning of both terms has developed and changed over a long period of time,<ref>{{Citation |last=Bezdek |first=James C. |title=Computational Intelligence Defined - By Everyone ! |date=1998 |work=Computational Intelligence: Soft Computing and Fuzzy-Neuro Integration with Applications |pages=10–37 |editor-last=Kaynak |editor-first=Okyay |url=https://www.researchgate.net/publication/239724199 |access-date=2025-02-03 |place=Berlin, Heidelberg |publisher=Springer |language=en |doi=10.1007/978-3-642-58930-0_2 |isbn=978-3-642-63796-4 |editor2-last=Zadeh |editor2-first=Lotfi A. |editor3-last=Türkşen |editor3-first=Burhan |editor4-last=Rudas |editor4-first=Imre J.}}</ref><ref>{{Cite book |last=Engelbrecht |first=Andries P. |url=https://www.worldcat.org/title/133465571 |title=Computational Intelligence: An Introduction |date=2007 |publisher=John Wiley & Sons |isbn=978-0-470-03561-0 |edition=2nd |location=Chichester, England ; Hoboken, NJ |pages=11–13 |language=en |chapter=Short History |oclc=133465571}}</ref> with AI being used first.<ref name=":1" /><ref name=":14" /> Bezdek describes this impressively and concludes that such buzzwords are frequently used and hyped by the scientific community, science management and (science) journalism.<ref name=":11" /> Not least because AI and biological intelligence are emotionally charged terms<ref name=":1" /><ref name=":11" /> and it is still difficult to find a generally accepted definition for the basic term ''intelligence''.<ref name=":1" /><ref name=":12" />