Editing Computational intelligence (section)

== The main algorithmic approaches of CI and their applications ==
The main applications of Computational Intelligence include computer science, engineering, [[data analysis]] and [[bio-medicine]].

=== Fuzzy logic ===
Unlike conventional Boolean logic, fuzzy logic is based on [[fuzzy set]]s. In both models, a property of an object is defined as belonging to a set; in fuzzy logic, however, the membership is not sharply defined by a yes/no distinction, but is graded gradually. This is done using [[Membership function (mathematics)|membership functions]] that assign a [[real number]] between 0 and 1 to each element as the degree of membership. The new set operations introduced in this way define the operations of an associated logic calculus that allows the modeling of [[Inference|inference processes]], i.e. [[logical reasoning]].<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=465–474 |language=en |chapter=Fuzzy Logic and Reasoning |oclc=133465571}}</ref> Therefore, fuzzy logic is well suited for engineering decisions without clear certainties and uncertainties or with imprecise data - as with natural language-processing technologies<ref name=":22">{{Cite web |last=Chai |first=Wesley |title=Fuzzy logic applications |url=https://www.techtarget.com/searchenterpriseai/definition/fuzzy-logic |access-date=2025-02-11 |website=What is Fuzzy Logic? - Definition from SearchEnterpriseAI}}</ref> but it doesn't have learning abilities.<ref name="Siddique2">{{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=4–5 |chapter=Fuzzy Logic}}</ref>

This technique tends to apply to a wide range of domains such as [[control engineering]],<ref>{{Cite book |last=Pedrycz |first=Witold |title=Fuzzy control and fuzzy systems |date=1993 |publisher=Research Studies Press [u.a.] |isbn=978-0-86380-131-0 |edition=2., extended, edition, reprint |series=Electronic & electrical engineering research studies Control theory and applications series |location=Taunton}}</ref> [[image processing]],<ref name=":26">{{Cite book |title=Fuzzy cluster analysis: methods for classification, data analysis, and image recognition |date=1999 |publisher=J. Wiley |isbn=978-0-471-98864-9 |editor-last=Höppner |editor-first=Frank |location=Chichester ; New York}}</ref> [[Fuzzy clustering|fuzzy data clustering]]<ref name=":26" /><ref>{{Cite journal |last=Dunn |first=J. C. |date=1973 |title=A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters |url= |journal=Journal of Cybernetics |language=en |volume=3 |issue=3 |pages=32–57 |doi=10.1080/01969727308546046 |issn=0022-0280}}</ref> and decision making.<ref name=":22" /> Fuzzy logic-based control systems can be found, for example, in the field of household appliances in washing machines, dish washers, microwave ovens, etc. or in the area of motor vehicles in gear transmission and braking systems. This principle can also be encountered when using a video camera, as it helps to stabilize the image when the camera is held unsteadily. Other areas such as medical diagnostics, satellite controllers and business strategy selection are just a few more examples of today's application of fuzzy logic.<ref name=":22" /><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=10–11 |language=en |chapter=Fuzzy Systems |oclc=133465571}}</ref>

=== Neural networks ===
An important field of CI is the development of [[artificial neural network]]s (ANN) based on the [[Biological neural network|biological ones]], which can be defined by three main components: the cell-body which processes the information, the axon, which is a device enabling the signal conducting, and the synapse, which controls signals.<ref name=":23">{{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=5–7 |language=en |chapter=Artificial Neural Networks |oclc=133465571}}</ref><ref>{{Cite book |last1=Eberhart |first1=Russell C. |url= |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=4–6 |language=en |chapter=Biological Basis for Neural Networks |doi=10.1016/B978-1-55860-759-0.X5000-8 |oclc=136781819}}</ref> Therefore, ANNs are very well suited for distributed information processing systems, enabling the process and the learning from experiential data.<ref name="Siddique_NN2">{{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=5 |chapter=Neural Networks}}</ref><ref name=":24">{{Cite journal |last1=Stergiou |first1=Christos |last2=Siganos |first2=Dimitrios |title=Neural Networks |url=http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html |url-status=dead |journal=SURPRISE 96 Journal |publisher=[[Imperial College London]] |archive-url=https://web.archive.org/web/20091216110504/http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html |archive-date=December 16, 2009 |access-date=March 11, 2015}}</ref> ANNs aim to mimic cognitive processes of the human brain. The main advantages of this technology therefore include fault tolerance, pattern recognition even with noisy images and the ability to learn.<ref name=":23" /><ref name=":24" />

Concerning its applications, neural networks can be classified into five groups: [[data analysis]] and [[Data classification (data management)|classification]], [[Content-addressable memory|associative memory]], [[data clustering]] or [[Data compression|compression]], generation of patterns, and [[control system]]s.<ref name=":25">{{Cite book |last1=Eberhart |first1=Russell C. |url= |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=12–13 |language=en |chapter=Neural Networks |doi=10.1016/B978-1-55860-759-0.X5000-8 |oclc=136781819}}</ref><ref name="Siddique_NN2" /><ref name=":23" /> The numerous applications include, for example, the analysis and classification of medical data, including the creation of [[Medical diagnosis|diagnoses]], [[speech recognition]], [[data mining]], [[Digital image processing|image processing]], [[forecasting]], [[robot control]], credit approval, pattern recognition, [[Face detection|face]] and fraud detection and dealing with nonlinearities of a system in order to control it.<ref name=":23" /><ref name="Siddique_NN2" /><ref name=":25" /> ANNs have the latter area of application and data clustering in common with fuzzy logic. Generative systems based on deep learning and convolutional neural networks, such as [[chatGPT]] or [[DeepL Translator|DeepL]], are a relatively new field of application.

=== Evolutionary computation ===
Evolutionary computation can be seen as a family of methods and algorithms for [[global optimization]], which are usually based on a [[Population model (evolutionary algorithm)|population]] of candidate solutions. They are inspired by [[biological evolution]] and are often summarized as [[evolutionary algorithm]]s.<ref>{{Cite book |last=De Jong |first=Kenneth A. |url=https://ieeexplore.ieee.org/book/6267245 |title=Evolutionary Computation: A Unified Approach. |publisher=MIT Press |year=2006 |isbn=978-0-262-52960-0 |location=Cambridge, MA |language=en}}</ref> These include the [[genetic algorithm]]s, [[evolution strategy]], [[genetic programming]] and many others.<ref>{{Cite book |last1=Eiben |first1=A.E. |url=https://link.springer.com/10.1007/978-3-662-44874-8 |title=Introduction to Evolutionary Computing |last2=Smith |first2=J.E. |date=2015 |publisher=Springer |isbn=978-3-662-44873-1 |series=Natural Computing Series |location=Berlin, Heidelberg |pages=99–116 |language=en |chapter=Popular Evolutionary Algorithm Variants |doi=10.1007/978-3-662-44874-8}}</ref> They are considered as problem solvers for tasks not solvable by traditional mathematical methods<ref>{{Cite book |last=De Jong |first=Kenneth A. |url=https://ieeexplore.ieee.org/book/6267245 |title=Evolutionary Computation: A Unified Approach |publisher=MIT Press |year=2006 |isbn=978-0-262-52960-0 |location=Cambridge, MA |pages=71–114 |language=en |chapter=Evolutionary Algorithms as Problem Solvers}}</ref> and are frequently used for [[Optimization (computer science)|optimization]] including [[multi-objective optimization]].<ref>{{Cite book |url=http://link.springer.com/10.1007/978-3-540-88908-3 |title=Multiobjective Optimization: Interactive and Evolutionary Approaches |date=2008 |publisher=Springer Berlin Heidelberg |isbn=978-3-540-88907-6 |editor-last=Branke |editor-first=Jürgen |series=Lecture Notes in Computer Science |volume=5252 |location=Berlin, Heidelberg |language=en |doi=10.1007/978-3-540-88908-3 |editor-last2=Deb |editor-first2=Kalyanmoy |editor-last3=Miettinen |editor-first3=Kaisa |editor-last4=Słowiński |editor-first4=Roman}}</ref> Since they work with a population of candidate solutions that are processed in parallel during an iteration, they can easily be distributed to different computer nodes of a cluster.<ref>{{Cite book |last=Cantú-Paz |first=Erick |title=Efficient and Accurate Parallel Genetic Algorithms |date=2001 |publisher=Springer US |isbn=978-1-4613-6964-6 |series=Genetic Algorithms and Evolutionary Computation |volume=1 |location=New York, NY |doi=10.1007/978-1-4615-4369-5}}</ref> As often more than one offspring is generated per pairing, the evaluations of these offspring, which are usually the most time-consuming part of the optimization process, can also be performed in parallel.<ref name=":72">{{Citation |last1=Khalloof |first1=Hatem |title=A Generic Flexible and Scalable Framework for Hierarchical Parallelization of Population-Based Metaheuristics |date=2020-11-02 |work=Proceedings of the 12th International Conference on Management of Digital EcoSystems (MEDES'20) |pages=124–131 |url=https://dl.acm.org/doi/10.1145/3415958.3433041 |location=New York, NY |publisher=ACM |language=en |doi=10.1145/3415958.3433041 |isbn=978-1-4503-8115-4 |s2cid=227179748 |last2=Mohammad |first2=Mohammad |last3=Shahoud |first3=Shadi |last4=Duepmeier |first4=Clemens |last5=Hagenmeyer |first5=Veit|url-access=subscription }}</ref>

In the course of optimization, the population learns about the structure of the search space and stores this information in the chromosomes of the solution candidates. After a run, this knowledge can be reused for similar tasks by adapting some of the “old” chromosomes and using them to seed a new population.<ref>{{Cite journal |last1=Jakob |first1=Wilfried |last2=Strack |first2=Sylvia |last3=Quinte |first3=Alexander |last4=Bengel |first4=Günther |last5=Stucky |first5=Karl-Uwe |last6=Süß |first6=Wolfgang |date=2013-04-22 |title=Fast Rescheduling of Multiple Workflows to Constrained Heterogeneous Resources Using Multi-Criteria Memetic Computing |journal=Algorithms |language=en |volume=6 |issue=2 |pages=245–277 |doi=10.3390/a6020245 |issn=1999-4893 |doi-access=free}}</ref><ref>{{Cite journal |last1=Friedrich |first1=Tobias |last2=Wagner |first2=Markus |date=August 2015 |title=Seeding the initial population of multi-objective evolutionary algorithms: A computational study |journal=Applied Soft Computing |language=en |volume=33 |pages=223–230 |doi=10.1016/j.asoc.2015.04.043|arxiv=1412.0307 }}</ref>

=== Swarm intelligence ===
Swarm intelligence is based on the collective behavior of decentralized, self-organizing systems, typically consisting of a population of simple agents that interact locally with each other and with their environment. Despite the absence of a centralized control structure that dictates how the individual agents should behave, local interactions between such agents often lead to the emergence of global behavior.<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 |isbn=978-1-118-33784-4 |location=Chichester, West Sussex, UK |pages=7–11 |language=en |chapter=Swarm Intelligence}}</ref><ref>{{Cite book |last1=Kennedy |first1=James |title=Swarm Intelligence |last2=Eberhart |first2=Russell C. |last3=Shi |first3=Yuhui |date=2001 |publisher=Morgan Kaufmann |isbn=978-1-55860-595-4 |edition= |series=The Morgan Kaufmann Series in Artificial Intelligence |location=San Francisco |language=en |doi=10.1016/B978-1-55860-595-4.X5000-1}}</ref><ref>{{Cite book |last1=Bonabeau |first1=Eric |title=Swarm Intelligence: From Natural to Artificial Systems |last2=Dorigo |first2=Marco |last3=Theraulaz |first3=Guy |date=1999 |publisher=Oxford University Press |isbn=978-0-19-513158-1 |location=New York |language=en}}</ref> Among the recognized representatives of algorithms based on swarm intelligence are [[particle swarm optimization]] and [[Ant colony optimization algorithms|ant colony optimization]].<ref>{{Cite book |last=Engelbrecht |first=Andries P. |title=Computational Intelligence: An Introduction |date=2007 |publisher=John Wiley & Sons |isbn=978-0-470-03561-0 |edition=2nd |location=Chichester, England ; Hoboken, NJ |page=9 |language=en |chapter=Swarm Intelligence |oclc=133465571}}</ref> Both are [[metaheuristic]] optimization algorithms that can be used to (approximately) solve difficult [[Mathematical optimization|numerical]] or complex [[combinatorial optimization]] tasks.<ref>{{Cite journal |last=Poli |first=Riccardo |date=January 2008 |editor-last=Vanneschi |editor-first=Leonardo |title=Analysis of the Publications on the Applications of Particle Swarm Optimisation |url= |journal=Journal of Artificial Evolution and Applications |language=en |volume=2008 |issue=1 |doi=10.1155/2008/685175 |issn=1687-6229 |doi-access=free}}</ref><ref>{{Cite journal |last1=Bhavya |first1=Ravinder |last2=Elango |first2=Lakshmanan |date=2023-04-27 |title=Ant-Inspired Metaheuristic Algorithms for Combinatorial Optimization Problems in Water Resources Management |journal=Water |language=en |volume=15 |issue=9 |pages=1712 |doi=10.3390/w15091712 |issn=2073-4441 |doi-access=free|bibcode=2023Water..15.1712B }}</ref><ref>{{Cite book |url= |title=Applications of Ant Colony Optimization and its Variants: Case Studies and New Developments |date=2024 |publisher=Springer Nature Singapore |isbn=978-981-99-7226-5 |editor-last=Dey |editor-first=Nilanjan |series=Springer Tracts in Nature-Inspired Computing |location=Singapore |language=en |doi=10.1007/978-981-99-7227-2}}</ref> Since both methods, like the evolutionary algorithms, are based on a population and also on local interaction, they can be easily parallelized<ref>{{Citation |last1=Li |first1=Bo |title=Parallelizing particle swarm optimization |date=2005 |work=IEEE Pacific Rim Conference on Communications, Computers and signal Processing (PACRIM 2005) |pages=288–291 |url=https://ieeexplore.ieee.org/document/1517282 |publisher=IEEE |doi=10.1109/PACRIM.2005.1517282 |isbn=978-0-7803-9195-6 |last2=Wada |first2=Koishi|url-access=subscription }}</ref><ref>{{Cite journal |last1=Randall |first1=Marcus |last2=Lewis |first2=Andrew |date=September 2002 |title=A Parallel Implementation of Ant Colony Optimization |url=https://linkinghub.elsevier.com/retrieve/pii/S074373150291854X |journal=Journal of Parallel and Distributed Computing |language=en |volume=62 |issue=9 |pages=1421–1432 |doi=10.1006/jpdc.2002.1854|hdl=10072/6633 |hdl-access=free }}</ref> and show comparable learning properties.<ref>{{Cite journal |last1=Zheng |first1=Rui-zhao |last2=Zhang |first2=Yong |last3=Yang |first3=Kang |date=2022-05-23 |title=A transfer learning-based particle swarm optimization algorithm for travelling salesman problem |url=https://academic.oup.com/jcde/article/9/3/933/6590609 |journal=Journal of Computational Design and Engineering |language=en |volume=9 |issue=3 |pages=933–948 |doi=10.1093/jcde/qwac039 |issn=2288-5048|doi-access=free }}</ref><ref>{{Cite journal |last1=Xing |first1=Li-Ning |last2=Chen |first2=Ying-Wu |last3=Wang |first3=Peng |last4=Zhao |first4=Qing-Song |last5=Xiong |first5=Jian |date=June 2010 |title=A Knowledge-Based Ant Colony Optimization for Flexible Job Shop Scheduling Problems |url=https://linkinghub.elsevier.com/retrieve/pii/S156849460900194X |journal=Applied Soft Computing |language=en |volume=10 |issue=3 |pages=888–896 |doi=10.1016/j.asoc.2009.10.006|url-access=subscription }}</ref>

=== Bayesian networks ===
In complex application domains, Bayesian networks provide a means to efficiently store and evaluate uncertain knowledge. A Bayesian network is a [[Graphical model|probabilistic graphical model]] that represents a set of random variables and their conditional dependencies by a [[directed acyclic graph]]. The probabilistic representation makes it easy to draw conclusions based on new information. In addition, Bayesian networks are well suited for learning from data.<ref name=":5" /> Their wide range of applications includes medical diagnostics, risk management, information retrieval, and text analysis, e.g. for spam filters. Their wide range of applications includes medical diagnostics, risk management, information retrieval, text analysis, e.g. for spam filters, credit rating of companies, and the operation of complex industrial processes.<ref>{{Cite book |last1=Pourret |first1=Olivier |title=Bayesian networks: a practical guide to applications |last2=Naïm |first2=Patrick |last3=Marcot |first3=Bruce Gregory |date=2008 |publisher=J. Wiley |isbn=978-0-470-06030-8 |series=Statistics in practice |location=Chichester (GB)}}</ref>

=== Artificial immune systems ===
Artificial immune systems are another group of population-based metaheuristic learning algorithms designed to solve clustering and optimization problems. These algorithms are inspired by the principles of theoretical immunology and the processes of the vertebrate immune system, and use the learning and memory properties of the immune system to solve a problem. Operators similar to those known from evolutionary algorithms are used to clone and mutate artificial lymphocytes.<ref name=":27">{{Citation |last1=Hošovský |first1=Alexander |title=Artificial Immune Systems |date=2021 |work=Implementing Industry 4.0 in SMEs |pages=48–52 |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><ref name=":28">{{Cite journal |last1=Cosma |first1=Georgina |last2=Brown |first2=David |last3=Archer |first3=Matthew |last4=Khan |first4=Masood |last5=Graham Pockley |first5=A. |date=March 2017 |title=A survey on computational intelligence approaches for predictive modeling in prostate cancer |url=https://linkinghub.elsevier.com/retrieve/pii/S0957417416306297 |journal=Expert Systems with Applications |language=en |volume=70 |pages=1–19 |doi=10.1016/j.eswa.2016.11.006}}</ref> Artificial immune systems offer interesting capabilities such as adaptability, self-learning, and robustness that can be used for various tasks in data processing,<ref name=":28" /> manufacturing systems,<ref>{{Cite journal |last1=Pinto |first1=Rui |last2=Gonçalves |first2=Gil |date=September 2022 |title=Application of Artificial Immune Systems in Advanced Manufacturing |journal=Array |language=en |volume=15 |pages=100238 |doi=10.1016/j.array.2022.100238 |doi-access=free}}</ref> system modeling and control, fault detection, or cybersecurity.<ref name=":27" />

=== Learning theory ===
Still looking for a way of "reasoning" close to the humans' one, [[computational learning theory|learning theory]] is one of the main approaches of CI. In psychology, learning is the process of bringing together cognitive, emotional and environmental effects and experiences to acquire, enhance or change knowledge, skills, values and world views.<ref>{{Cite book |last=Ormrod |first=Jeanne Ellis |title=Educational Psychology: Principles and Applications |date=1995 |publisher=Merrill [u.a.] |isbn=978-0-675-21086-7 |edition=1st |location=Englewood Cliffs, NJ |language=en}}</ref><ref>{{Cite book |last1=Illeris |first1=Knud |title=The three dimensions of learning: contemporary learning theory in the tension field between the cognitive, the emotional, and the social |last2=Illeris |first2=Knud |date=2004 |publisher=Krieger |isbn=978-1-57524-258-3 |edition=Reprint |location=Malabar, FL}}</ref><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=6 |chapter=Learning Theory}}</ref> Learning theories then helps understanding how these effects and experiences are processed, and then helps making predictions based on previous experience.<ref>{{Cite web|url = https://www.cs.ox.ac.uk/teaching/courses/2014-2015/clt/|title = Computational Learning Theory: 2014-2015|access-date = February 11, 2015|website = University of Oxford |last = Worrell|first = James|others = Presentation page of CLT course}}</ref>

=== Probabilistic methods ===
Being one of the main elements of fuzzy logic, probabilistic methods firstly introduced by [[Paul Erdős|Paul Erdos]] and [[Joel Spencer]] in 1974,<ref>{{Cite book |last1=Erdős |first1=Paul |title=Probabilistic methods in combinatorics |last2=Spencer |first2=Joel H. |date=1974 |publisher=Academic Press |isbn=978-0-12-240960-8 |series=Probability and mathematical statistics, 17 |location=New York}}</ref><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=6–7 |chapter=Probabilistic Methods}}</ref> aim to evaluate the outcomes of a Computation Intelligent system, mostly defined by [[randomness]].<ref>{{Cite book|title = Computational Intelligence in Time Series Forecasting : Theory and Engineering Applications|last1 = Palit |first1 = Ajoy K. |last2=Popovic |first2=Dobrivoje |publisher = Springer Science & Business Media |year = 2006 |isbn = 9781846281846 |page = 4}}</ref> Therefore, probabilistic methods bring out the possible solutions to a problem, based on prior knowledge.