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.{{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}} 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{{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=}}

File:Relationship AI-HC CI-SC.svgThe 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

• 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 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.{{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}}{{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.}} 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. The adjacent figure illustrates these relationships and lists the most important CI techniques. Another frequently mentioned distinguishing feature is the representation of information in symbolic form in AI and in sub-symbolic form in CI techniques.{{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}}

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 logic (also called crisp logic{{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}}), 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.{{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}}{{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}}{{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}}{{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}}

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. 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.

AI and CI are catchy terms, 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,{{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.}}{{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}} with AI being used first. Bezdek describes this impressively and concludes that such buzzwords are frequently used and hyped by the scientific community, science management and (science) journalism. Not least because AI and biological intelligence are emotionally charged terms and it is still difficult to find a generally accepted definition for the basic term intelligence.

In 1950, Alan Turing, one of the founding fathers of computer science, developed a test for computer intelligence known as the Turing test.{{Cite journal |last=Turing |first=Alan M. |date=1950-10-01 |title=I.—COMPUTING MACHINERY AND INTELLIGENCE |url=https://academic.oup.com/mind/article/LIX/236/433/986238 |journal=Mind |language=en |volume=LIX |issue=236 |pages=433–460 |doi=10.1093/mind/LIX.236.433 |issn=1460-2113|url-access=subscription }} In this test, a person can ask questions via a keyboard and a monitor without knowing whether his counterpart is a human or a computer. A computer is considered intelligent if the interrogator cannot distinguish the computer from a human. This illustrates the discussion about intelligent computers at the beginning of the computer age.

The term Computational Intelligence was first used as the title of the journal of the same name in 1985{{Cite web |title=Computational Intelligence - Issue archive |url=https://onlinelibrary.wiley.com/loi/14678640/year/1985 |website=Wiley Online Library|doi=10.1111/(ISSN)1467-8640 }}{{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=2025-02-01 |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.}} and later by the IEEE Neural Networks Council (NNC), which was founded 1989 by a group of researchers interested in the development of biological and artificial neural networks.{{Cite web |date=July 22, 2014 |title=IEEE Computational Intelligence Society History |url=http://ethw.org/IEEE_Computational_Intelligence_Society_History |access-date=2015-10-30 |website=Engineering and Technology history Wiki}} On November 21, 2001, the NNC became the IEEE Neural Networks Society, to become the IEEE Computational Intelligence Society two years later by including new areas of interest such as fuzzy systems and evolutionary computation.

The NNC helped organize the first IEEE World Congress on Computational Intelligence in Orlando, Florida in 1994. On this conference the first clear definition of Computational Intelligence was introduced by Bezdek: A system is computationally intelligent when it: deals with only numerical (low-level) data, has pattern-recognition components, does not use knowledge in the AI sense; and additionally when it (begins to) exhibit (1) computational adaptivity; (2) computational fault tolerance; (3) speed approaching human-like turnaround and (4) error rates that approximate human performance.{{Cite book |last=Bezdek |first=James C |title=Computational Intelligence: Imitating Life |date=1994 |publisher=IEEE Press |isbn=978-0-7803-1104-6 |editor-last=Zurada |editor-first=Jacek M. |edition= |location=New York, NY |pages=1–12 |chapter=What is computational intelligence? |editor-last2=Marks II |editor-first2=Robert J. |editor-last3=Robinson |editor-first3=Charles J.}}

Today, with machine learning and deep learning in particular utilizing a breadth of supervised, unsupervised, and reinforcement learning approaches, the CI landscape has been greatly enhanced, with novell intelligent approaches.

The main applications of Computational Intelligence include computer science, engineering, data analysis and bio-medicine.

Unlike conventional Boolean logic, fuzzy logic is based on fuzzy sets. 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 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 processes, i.e. logical reasoning.{{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}} Therefore, fuzzy logic is well suited for engineering decisions without clear certainties and uncertainties or with imprecise data - as with natural language-processing technologies{{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}} but it doesn't have learning abilities.{{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}}

This technique tends to apply to a wide range of domains such as control engineering,{{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}} image processing,{{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}} fuzzy data clustering{{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}} and decision making. 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.{{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}}

An important field of CI is the development of artificial neural networks (ANN) based on the 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.{{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}}{{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}} Therefore, ANNs are very well suited for distributed information processing systems, enabling the process and the learning from experiential data.{{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}}{{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}} 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.

Concerning its applications, neural networks can be classified into five groups: data analysis and classification, associative memory, data clustering or compression, generation of patterns, and control systems.{{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}} The numerous applications include, for example, the analysis and classification of medical data, including the creation of diagnoses, speech recognition, data mining, image processing, forecasting, robot control, credit approval, pattern recognition, face and fraud detection and dealing with nonlinearities of a system in order to control it. 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, are a relatively new field of application.

Evolutionary computation can be seen as a family of methods and algorithms for global optimization, which are usually based on a population of candidate solutions. They are inspired by biological evolution and are often summarized as evolutionary algorithms.{{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}} These include the genetic algorithms, evolution strategy, genetic programming and many others.{{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}} They are considered as problem solvers for tasks not solvable by traditional mathematical methods{{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}} and are frequently used for optimization including multi-objective optimization.{{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}} 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.{{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}} 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.{{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 }}

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.{{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}}{{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 }}

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.{{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}}{{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}}{{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}} Among the recognized representatives of algorithms based on swarm intelligence are particle swarm optimization and ant colony optimization.{{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}} Both are metaheuristic optimization algorithms that can be used to (approximately) solve difficult numerical or complex combinatorial optimization tasks.{{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}}{{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 }}{{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}} Since both methods, like the evolutionary algorithms, are based on a population and also on local interaction, they can be easily parallelized{{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 }}{{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 }} and show comparable learning properties.{{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 }}{{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 }}

In complex application domains, Bayesian networks provide a means to efficiently store and evaluate uncertain knowledge. A Bayesian network is a 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. 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.{{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)}}

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.{{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}}{{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}} Artificial immune systems offer interesting capabilities such as adaptability, self-learning, and robustness that can be used for various tasks in data processing, manufacturing systems,{{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}} system modeling and control, fault detection, or cybersecurity.

Still looking for a way of "reasoning" close to the humans' one, 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.{{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}}{{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}}{{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}} Learning theories then helps understanding how these effects and experiences are processed, and then helps making predictions based on previous experience.{{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}}

Being one of the main elements of fuzzy logic, probabilistic methods firstly introduced by Paul Erdos and Joel Spencer in 1974,{{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}}{{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}} aim to evaluate the outcomes of a Computation Intelligent system, mostly defined by randomness.{{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}} Therefore, probabilistic methods bring out the possible solutions to a problem, based on prior knowledge.

According to bibliometrics studies, computational intelligence plays a key role in research.{{cite journal |doi=10.1142/s0218488507004911 |year=2007 |publisher=World Scientific Pub Co Pte Lt |volume=15 |number=5 |pages=625–645 |author=NEES JAN VAN ECK and LUDO WALTMAN |title=Bibliometric Mapping of the Computational Intelligence Field |journal=International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems |hdl=1765/10073 |url=http://repub.eur.nl/pub/10073 |hdl-access=free }} All the major academic publishers are accepting manuscripts in which a combination of Fuzzy logic, neural networks and evolutionary computation is discussed. On the other hand, Computational intelligence isn't available in the university curriculum.{{cite journal |title=Computational Intelligence Course in Undergraduate Computer Science and Engineering Curricula |author=Minaie, Afsaneh and Sanati-Mehrizy, Paymon and Sanati-Mehrizy, Ali and Sanati-Mehrizy, Reza |journal=Age |volume=23 |pages=1 |year=2013 |url=https://peer.asee.org/19330.pdf}} The amount of technical universities in which students can attend a course is limited. Only British Columbia, Technical University of Dortmund (involved in the European fuzzy boom) and Georgia Southern University are offering courses from this domain.

The reason why major university are ignoring the topic is because they don't have the resources. The existing computer science courses are so complex, that at the end of the semester there is no room for fuzzy logic.{{cite journal |doi=10.1109/mci.2011.941591 |year=2011 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=6 |number=3 |pages=57–59 |author=Mengjie Zhang |title=Experience of Teaching Computational Intelligence in an Undergraduate Level Course [Educational Forum] |journal=IEEE Computational Intelligence Magazine }} Sometimes it is taught as a subproject in existing introduction courses, but in most cases the universities are preferring courses about classical AI concepts based on Boolean logic, turing machines and toy problems like blocks world.

Since a while with the upraising of STEM education, the situation has changed a bit.{{cite conference |title=Computational intelligence: a Tool for Multidisciplinary Education and Research |author=Samanta, Biswanath |conference=Proceedings of the 2011 ASEE Northeast Section Annual Conference, University of Hartford |year=2011 }} There are some efforts available in which multidisciplinary approaches are preferred which allows the student to understand complex adaptive systems.{{cite journal |doi=10.1109/mci.2008.930983 |year=2009 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=4 |number=1 |pages=14–23 |author=G.K.K. Venayagamoorthy |title=A successful interdisciplinary course on computational intelligence |journal=IEEE Computational Intelligence Magazine }} These objectives are discussed only on a theoretical basis. The curriculum of real universities wasn't adapted yet.

• IEEE Transactions on Neural Networks and Learning Systems
• IEEE Transactions on Fuzzy Systems
• IEEE Transactions on Evolutionary Computation
• IEEE Transactions on Emerging Topics in Computational Intelligence
• IEEE Transactions on Autonomous Mental Development
• IEEE/ACM Transactions on Computational Biology and Bioinformatics
• IEEE Transactions on Computational Intelligence and AI in Games
• [https://onlinelibrary.wiley.com/journal/4795 Applied Computational Intelligence and Soft Computing]

{{columns-list|colwidth=30em|* AI effect

• Cognitive robotics
• Computational finance and Computational economics
• Concept mining
• Developmental robotics
• Data mining
• Evolutionary robotics
• ELIZA effect
• Knowledge-based engineering
• Natural computing
• Synthetic intelligence
• International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics

}}

• [http://ci.cs.up.ac.za Computational Intelligence: An Introduction] by Andries Engelbrecht. Wiley & Sons. {{ISBN|0-470-84870-7}}
• [http://www.cs.ubc.ca/~poole/ci.html Computational Intelligence: A Logical Approach] by David Poole, Alan Mackworth, Randy Goebel. Oxford University Press. {{ISBN|0-19-510270-3}}
• Computational Intelligence: A Methodological Introduction by Kruse, Borgelt, Klawonn, Moewes, Steinbrecher, Held, 2013, Springer, {{ISBN|9781447150121}}

{{Reflist}}

Category:Artificial intelligence