Editing Computational intelligence (section)

{{Short description|Ability of a computer to learn a specific task from data or experimental observation}}
{{for|the journal|Computational Intelligence (journal)}}
{{broader|Artificial intelligence}}

{{use mdy dates|date=October 2016}}
{{use American English|date=October 2016}}

In [[computer science]], '''computational intelligence''' ('''CI''') refers to [[concept]]s, [[paradigm]]s, [[algorithm]]s and [[implementation]]s of [[system]]s that are designed to show "[[Intelligence|intelligent]]" behavior in complex and changing environments.<ref name=":0" /> These systems are aimed at mastering complex tasks in a wide variety of technical or commercial areas and offer solutions that [[Pattern recognition|recognize and interpret patterns]], control processes, support [[decision-making]] or autonomously manoeuvre [[vehicle]]s or [[robot]]s in unknown environments, among other things.<ref name=":2" /> These concepts and paradigms are characterized by the ability to [[Learning|learn]] or [[Adaptation|adapt]] to new situations, to [[Generalization|generalize]], to [[Abstraction|abstract]], to discover and [[Association rule learning|associate]].<ref name=":1">{{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=3–4 |language=en |chapter=Introduction to Computational Intelligence |oclc=133465571}}</ref> Nature-analog or [[Natural computing#Nature-inspired models of computation|nature-inspired methods]] play a key role, such as in [[neuroevolution]] for '''Computational Intelligence'''.<ref name=":0">{{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 |date=2022 |publisher=Springer International Publishing |isbn=978-3-030-42226-4 |edition=3rd |series=Texts in Computer Science |location=Cham |pages=V |language=en |chapter=Preface |doi=10.1007/978-3-030-42227-1}}</ref>

CI approaches primarily address those complex real-world problems for which mathematical or traditional modeling is not appropriate for various reasons: the processes cannot be described exactly with complete knowledge, the processes are too [[Complexity|complex]] for [[mathematical reasoning]], they contain some uncertainties during the process, such as unforeseen changes in the environment or in the process itself, or the processes are simply [[stochastic]] in nature. Thus, CI techniques are properly aimed at processes that are [[ill-defined]], complex, [[Nonlinear system|nonlinear]], time-varying and/or stochastic.<ref>{{Cite book |last1=Siddique |first1=N. H. |title=Computational intelligence: synergies of fuzzy logic, neural networks, and evolutionary computing |last2=Adeli |first2=Hojjat |date=2013 |publisher=John Wiley & Sons Inc |isbn=978-1-118-53481-6 |location=Chichester, West Sussex, United Kingdom |pages=1–2 |chapter=Computational Intelligence}}</ref>

A recent definition of the [[Institute of Electrical and Electronics Engineers|IEEE]] [[Institute of Electrical and Electronics Engineers#Technical societies|Computational Intelligence Societey]] describes CI as ''the theory, design, application and development of biologically and linguistically motivated computational paradigms. Traditionally the three main pillars of CI have been [[Neural network|Neural Networks]], [[Fuzzy control system|Fuzzy Systems]] and [[Evolutionary computation|Evolutionary Computation]]. ... CI is an evolving field and at present in addition to the three main constituents, it encompasses computing paradigms like [[ambient intelligence]], [[artificial life]], [[cultural learning]], artificial endocrine networks, social reasoning, and artificial hormone networks. ... Over the last few years there has been an explosion of research on [[Deep learning|Deep Learning]], in particular [[Convolutional neural network|deep convolutional neural networks]]. Nowadays, deep learning has become the core method for [[artificial intelligence]]. In fact, some of the most successful AI systems are based on CI.''<ref name=":15">{{Cite web |title=What is Computational Intelligence? |url=https://cis.ieee.org/about/what-is-ci |access-date=2025-01-18 |website=IEEE Computational Intelligence Society}}</ref> However, as CI is an emerging and developing field there is no final definition of CI,<ref name=":10">{{Cite book |last1=Siddique |first1=Nazmul |title=Computational intelligence: synergies of fuzzy logic, neural networks, and evolutionary computing |last2=Adeli |first2=Hojjat |date=2013 |publisher=John Wiley & Sons Inc |isbn=978-1-118-33784-4 |location=Chichester, West Sussex, United Kingdom |pages=2–3 |language=en |chapter=Paradigms of Computational Intelligence}}</ref><ref>{{Cite journal |last=Bezdek |first=James C. |date=April 2016 |title=(Computational) Intelligence: What's in a Name? |url=https://ieeexplore.ieee.org/document/7549228 |journal=IEEE Systems, Man, and Cybernetics Magazine |volume=2 |issue=2 |page=11 |doi=10.1109/MSMC.2016.2558778 |issn=2333-942X|url-access=subscription }}</ref><ref name=":13" /> especially in terms of the list of concepts and paradigms that belong to it.<ref name=":1" /><ref name=":14">{{Cite book |last=Duch |first=Włodzisław |title=Challenges for Computational Intelligence |date=2007 |publisher=Springer |isbn=978-3-540-71983-0 |editor-last=Duch |editor-first=Włodzisław |series=Studies in Computational Intelligence |volume=63 |location=Berlin, Heidelberg |pages=1–13 |language=en |chapter=What Is Computational Intelligence and Where Is It Going? |doi=10.1007/978-3-540-71984-7 |editor-last2=Mańdziuk |editor-first2=Jacek}}</ref><ref name=":12">{{Cite book |last=Fulcher |first=John |title=Computational Intelligence: A Compendium |date=2008 |publisher=Springer |isbn=978-3-540-78292-6 |editor-last=Fulcher |editor-first=John |series=Studies in Computational Intelligence |volume=115 |location=Berlin, Heidelberg |pages=3–7 |language=en |chapter=Introduction, Overview, Definitions |doi=10.1007/978-3-540-78293-3 |editor-last2=Jain |editor-first2=L.C.}}</ref>

The general requirements for the development of an “intelligent system” are ultimately always the same, namely the simulation of intelligent thinking and action in a specific area of application. To do this, the knowledge about this area must be represented in a model so that it can be processed. The quality of the resulting system depends largely on how well the model was chosen in the development process. Sometimes [[Data-driven model|data-driven]] methods are suitable for finding a good model and sometimes logic-based knowledge representations deliver better results. Hybrid models are usually used in real applications.<ref name=":2">{{Cite book |last1=Kruse |first1=Rudolf |title=Computational Intelligence: A Methodological Introduction |last2=Mostaghim |first2=Sanaz |last3=Borgelt |first3=Christian |date=2022 |publisher=Springer International Publishing |isbn=978-3-030-42226-4 |edition=3rd |series=Texts in Computer Science |location=Cham |pages=1–2 |language=en |chapter=Intelligent Systems |doi=10.1007/978-3-030-42227-1}}</ref>

According to actual textbooks, the following methods and paradigms, which largely complement each other, can be regarded as parts of CI:<ref name=":3">{{Cite book |last=Engelbrecht |first=Andries P. |title=Computational intelligence: an introduction |date=2002 |publisher=J. Wiley & Sons |isbn=978-0-470-03561-0 |edition=2nd |location=Chichester, England ; Hoboken, N.J |pages=4–11 |language=en |chapter=Computational Intelligence Paradigms |oclc=133465571}}</ref><ref name=":4">{{Cite book |last1=Siddique |first1=Nazmul |title=Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks, and Evolutionary Computing |last2=Adeli |first2=Hojjat |date=2013 |publisher=John Wiley & Sons Inc |isbn=978-1-118-33784-4 |location=Chichester, West Sussex, United Kingdom |pages=3–10 |language=en |chapter=Approaches to Computational Intelligence}}</ref><ref name=":5">{{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 |date=2022 |publisher=Springer International Publishing |isbn=978-3-030-42226-4 |edition=3rd |series=Texts in Computer Science |location=Cham |pages=2–3 |language=en |chapter=Computational Intelligence |doi=10.1007/978-3-030-42227-1}}</ref><ref name=":6">{{Cite book |last1=Eberhart |first1=Russell C. |title=Computational Intelligence: Concepts to Implementations |last2=Shi |first2=Yuhui |date=2007 |publisher=Elsevier/Morgan Kaufmann Publishers |isbn=978-1-55860-759-0 |location=Amsterdam, Boston |pages=XIII-XIX |language=en |chapter=Preface}}</ref><ref name=":7">{{Cite book |last1=Hanne |first1=Thomas |title=Computational Intelligence in Logistics and Supply Chain Management |last2=Dornberger |first2=Rolf |date=2017 |publisher=Springer-Verlag |isbn=978-3-319-40722-7 |series=International series in operations research & management science |location= |pages=13–41 |chapter=Computational Intelligence |doi=10.1007/978-3-319-40722-7}}</ref><ref name=":8">{{Cite book |url= |title=Computational Intelligence Systems in Industrial Engineering: With Recent Theory and Applications |date=2012 |publisher=Atlantis Press |isbn=978-94-91216-76-3 |editor-last=Kahraman |editor-first=Cengiz |series=Atlantis Computational Intelligence Systems |volume=6 |location=Paris |pages=VII-XI |language=en |chapter=Preface |doi=10.2991/978-94-91216-77-0}}</ref><ref name=":9">{{Citation |last1=Hošovský |first1=Alexander |title=Computational Intelligence in the Context of Industry 4.0 |date=2021 |work=Implementing Industry 4.0 in SMEs |pages=30–31 |editor-last=Matt |editor-first=Dominik T. |place=Cham |publisher=Springer International Publishing |language=en |doi=10.1007/978-3-030-70516-9_2 |isbn=978-3-030-70515-2 |last2=Piteľ |first2=Ján |last3=Trojanová |first3=Monika |last4=Židek |first4=Kamil |editor2-last=Modrák |editor2-first=Vladimír |editor3-last=Zsifkovits |editor3-first=Helmut}}</ref>

* Fuzzy systems<ref name=":3" /><ref name=":4" /><ref name=":5" /><ref name=":6" /><ref name=":7" /><ref name=":8" /><ref name=":9" />
* Neural networks<ref name=":3" /><ref name=":4" /><ref name=":6" /><ref name=":7" /> and, in particular, convolutional neural networks<ref name=":5" /><ref name=":8" /><ref name=":9" />
* Evolutionary computation<ref name=":6" /><ref name=":7" /> and, in particular, multi-objective evolutionary optimization<ref name=":3" /><ref name=":4" /><ref name=":5" /><ref name=":8" /><ref name=":9" />
* [[Swarm intelligence]]<ref name=":3" /><ref name=":4" /><ref name=":5" /><ref name=":6" /><ref name=":7" /><ref name=":8" /><ref name=":9" />
* [[Bayesian network]]s<ref name=":5" /><ref name=":8" /><ref name=":9" />
* [[Artificial immune system]]s<ref name=":7" /><ref name=":9" />
* [[Statistical learning theory|Learning theory]]<ref name=":4" />
* [[Probabilistic method|Probabilistic Methods]]<ref name=":4" />