Revision 952080888 of "Draft:Soft computing" on enwiki

{{AFC submission|d|mergeto|Computational intelligence|u=ManuelRodriguez|ns=118|decliner=AngusWOOF|declinets=20200309160440|ts=20200309093942}} <!-- Do not remove this line! -->

{{AFC comment|1=This should be discussed whether this needs to be a separate article from computational intelligence. [[User:AngusWOOF|<strong><span style="color: #606060;">AngusWOOF</span></strong>]] ([[User talk:AngusWOOF#top|<span style=" color: #663300;">bark</span>]] • [[Special:Contributions/AngusWOOF|<span style="color: #006600;">sniff</span>]]) 16:04, 9 March 2020 (UTC)}}

----

{{Distinguish|soft microprocessor}}

{{Draft}}

{{Multiple issues|
{{Expert needed|computer science|date=July 2009}}
{{Notability|date=August 2019}}
{{Essay-like|date=August 2019}}
{{Confusing|date=August 2019}}
{{Incomprehensible|date=August 2019}}
{{Unfocused|date=August 2019}}
}}

[[File:Soft Computing pic.jpg|thumb|Soft Computing diagram]]
'''Soft computing''' is a branch of computer science that seeks to imitate human intelligence, learning and decision making by the employment of various methods.  Soft computing employs [[fuzzy logic]], rough sets, artificial neural networks, and various evolutionary algorithms and search strategies to further these ends.{{sfn|Samir|Chakraborty|2013}} 

Whereas mainstream computing is referred to as  "hard computing",{{sfn|Seising|2011|pp=3-36}}<!--uneccesary reference. Move elsewhere--> soft computing claims to bypass existing bottlenecks in science with a strong bias towards [[semiotics]] {{sfn|Gudwin|1999}}{{sfn|Rieger|1998}} and imprecise knowledge.{{sfn|Ibrahim|2016|pp=34-38}} 

==History==

The phrase ''soft computing'' was coined in the 1990s by [[Lotfi A. Zadeh]], a pioneer in the field. Zadeh was also a pioneer in the related field of ''Fuzzy logic'' and the concept of [[fuzzy sets]]. According to soft computing [[advocacy group]]s, hard computing is not equipped  to analyze cognitive processes.{{sfn|Gudwin|1999|p=160}} 

Soft computing, as opposed to traditional computing, deals with approximate models and gives solutions to complex real-life problems such as [[fuzzy control system]]s, fuzzy graph theory{{sfn|Sunitha|Sunil|2013}}, [[fuzzy systems]], and so on.   Zadeh observed that people are good at 'soft' thinking while computers typically are 'hard' thinking.{{sfn|Jin|2014}}  People use concepts like 'some', 'most', or 'very' rather than 'hard' or precise concepts, values and quantities. People want a 'warm' glass of milk, not one that is 41 degrees C. In general, people are good at learning, finding patterns, adapting and are rather unpredictable.  In 'hard' computing, by contrast, machines need precision, determinism and  measures, and although pattern recognition happens, there is a brittleness if things change - such systems cannot easily adapt. 'Soft' computing by contrast embraces chaotic, neural models of computing that are more pliable.  Soft computing involves using a combination of methods that are designed to approximate human learning, decision making and intelligence. 

Early soft computational approaches could model and precisely analyze only relatively simple systems. More complex systems arising in [[biology]], [[medicine]], the [[humanities]], [[management science]]s, and similar fields often remained intractable to conventional mathematical and analytical methods.

Soft computing deals with imprecision, uncertainty, partial truth, and approximation to achieve computability, robustness and low solution cost. As such it forms the basis of a considerable amount of [[machine learning]] techniques. Recent trends tend to involve evolutionary and swarm intelligence based algorithms and [[bio-inspired computation]].{{sfn|Yang|2013}}{{sfn|Chaturvedi|2008}}

Generally speaking, soft computing techniques resemble biological processes more closely than traditional techniques, which are largely based on formal [[logical system]]s, such as [[sentential logic]] and [[predicate logic]], or rely heavily on computer-aided numerical analysis (as in [[finite element analysis]]). Soft computing techniques are intended to complement each other.

Unlike hard computing schemes, which strive for exactness and formal proof, soft computing techniques exploit the given tolerance of imprecision, partial truth, and uncertainty for a particular problem. Another common contrast comes from the observation that [[inductive reasoning]] plays a larger role in soft computing than in hard computing.

Research in soft computing have demonstrated some practical examples,{{sfn|Zhou|2000|pp=238-250}}{{sfn|Karray|2002}} such as Neuron [[MOS transistor]]s {{sfn|Shibata|1999|pp=648-656}} and emotional pets.{{sfn|Dote|2001}}

Within the history of Artificial Intelligence there is a trend towards including [[linguistics]] and probability theory into existing software frameworks.{{sfn|Seising |2013}} The highly successful innovation of [[deep learning]] is based on the idea, that input data is transformed into abstract representation.

==Beyond Turing machines==
[[File:BQP complexity class diagram.svg|thumb|BQP complexity class diagram]]
In classical so called hard computing there is a bottleneck available<ref>{{cite conference |doi=10.1007/978-1-4471-1599-1_111 |year=1998 |publisher=Springer London |pages=725--730 |author=B. Sick and M. Keidl and M. Ramsauer and S. Seltzsam |title=A Comparison of Traditional and Soft-Computing Methods in a Real-Time Control Application |conference=ICANN 98 }}</ref> which has to do how a turing machine is working. For solving a task, a turing machine needs a certain amount of steps, which are executed by the algorithm. If an algorithm needs to much steps to solve a problem, it's called an np hard problem, which means, that every turing machine fails to solve this sort of problem.

Soft computing claims to bypass the Turing limit by introducing a different kind of computational paradigm, which is called a super-turing machine.<ref>{{cite conference |doi=10.1109/wcica.2006.1713000 |year=2006 |publisher=IEEE |author=Yongming Li |title=Some Results of Fuzzy Turing Machines |conference=2006 6th World Congress on Intelligent Control and Automation }}</ref><ref>{{cite journal |doi=10.1016/j.biosystems.2004.05.032 |year=2004 |publisher=Elsevier BV |volume=77 |number=1-3 |pages=175--194 |author=Cristian S. Calude and Gheorghe P\uaun |title=Bio-steps beyond Turing |journal=Biosystems }}</ref> Super Turing machines are able to solve all the np hard problems by grounding the algorithm to the outside world.<ref>{{cite journal |doi=10.1016/s0921-8890(03)00021-6 |year=2003 |publisher=Elsevier BV |volume=43 |number=2-3 |pages=85--96 |author=Silvia Coradeschi and Alessandro Saffiotti |title=An introduction to the anchoring problem |journal=Robotics and Autonomous Systems }}</ref> Grounding means to connect the numerical values in a fuzzy set with natural language terms which are describing the problem.<ref>{{cite journal |doi=10.1142/s1793351x10001061 |year=2010 |publisher=World Scientific Pub Co Pte Lt |volume=04 |number=03 |pages=331--356 |author=YINGXU WANG |title=ON CONCEPT ALGEBRA FOR COMPUTING WITH WORDS (CWW) |journal=International Journal of Semantic Computing }}</ref> The discipline of granular computing<ref>{{cite conference |title=The roots of granular computing |author=Bargiela, Andrzej and Pedrycz, Witold |conference=2006 IEEE International Conference on Granular Computing |pages=806--809 |year=2006 |publisher=IEEE }}</ref> is equal to soft computing and can be interpreted as the opposite to classical hard computing.

==References==
{{reflist}}

==Bibliography==
*{{cite book |last1=Samir |first1=Rov |last2=Chakraborty |first2=Udit |title=Introduction to soft computing : neuro-fuzzy and genetic algorithms |date=3 June 2013 |publisher=Pearson |isbn=978-8131792469 |ref=harv }}
* {{cite book |doi=10.1007/978-3-642-24672-2_1 |isbn=978-3-642-24671-5 |date=2011 |publisher=Springer Berlin Heidelberg |first1=Rudolf |last1=Seising |first2=Veronica | last2=Sanz  |title=From Hard Science and Computing to Soft Science and Computing An Introductory Survey |chapter=From Hard Science and Computing to Soft Science and Computing – an Introductory Survey |volume=273 |conference=Soft Computing in Humanities and Social Sciences |series=Studies in Fuzziness and Soft Computing |ref=harv}}
* {{cite conference |title=From semiotics to computational semiotics |last1=Gudwin |first1=Ricardo R |conference=Proceedings of the 9th International Congress of the German Society for Semiotic Studies, 7th International Congress of the International Association for Semiotic Studies (IASS/AIS) |date=1999 | ref=harv }}
* {{cite conference |title=Computing Fuzzy Semantic Granules from Natural Language Texts |last1=Rieger|first1=B |conference=Proc. 7th IPMU Conf. |pages=475–479 |date=1998 |ref=harv }}
* {{cite journal |doi=10.1016/j.procs.2016.09.366 |date=2016 |publisher=Elsevier BV |volume=102 |pages=34–38 |last1=Ibrahim |first1=Dogan  |title=An Overview of Soft Computing |journal=Procedia Computer Science |ref=harv }}
* {{cite journal |doi=10.2991/ijcis.2010.3.2.4 |date=2010 |publisher=Atlantis Press |volume=3 |number=2 |first1=Rudolf |last1=Seising  |title=What is Soft Computing? Bridging Gaps for 21st Century Science! |journal=International Journal of Computational Intelligence Systems| ref=harv }}
* {{cite journal |doi=10.1007/s005000000053 |date=2000 |publisher=Springer Science and Business Media LLC |volume=4 |number=4 |pages=238–250 |last1=Zhou |first1=C |title=Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot |journal=Soft Computing| ref=harv  }}
* {{cite journal |doi=10.1109/3477.979962 |pmid=18238106 |date=2002 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=32 |number=1 |pages=77–90 |last1=Karray|first1=F |last2=Gueaieb|first2=W |last3=Al-Sharhan|first3=S |title=The hierarchical expert tuning of PID controllers using tools of soft computing |journal=IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics)| ref=harv  }}
* {{cite conference |title=Soft-computing integrated circuits for intelligent information processing |last1=Shibata|first1=Tadashi|last2=Yagi|first2=Masakazu|last3=Adachi|first3=Masayoshi |conference=Proceedings of The Second International Conference on Information Fusion |volume=1 |pages=648–656 |date=1999| ref=harv  }}
* {{cite journal |doi=10.1109/5.949483 |date=2001 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=89 |number=9 |pages=1243–1265 |last1= Dote|first1=Y|last2=Ovaska|first2=S.J.  |title=Industrial applications of soft computing: a review |journal=Proceedings of the IEEE| ref=harv  }}
* {{cite conference |doi=10.1109/ifsa-nafips.2013.6608492 |date=2013 |publisher=IEEE |first1=Rudolf |last1=Seising |first2=Tabacchi|last2=Marco Elio  |title=A very brief history of soft computing: Fuzzy Sets, artificial Neural Networks and Evolutionary Computation |conference=2013 Joint IFSA World Congress and NAFIPS Annual }}
* {{cite book |first1=X. S. |last1=Yang|first2=Z. H. |last2=Cui |first3=R. |last3=Xiao |first4=A. |last4=Gandomi |first5=M. |last5=Karamanoglu | url=https://books.google.com/books?id=J0VcBQxtcwsC&printsec=frontcover#v=onepage&q=%22soft%20computing%22&f=false | title=Swarm Intelligence and Bio-Inspired Computation: Theory and Applications | publisher=Elsevier |date=2013 |ref=harv}}
* {{cite book |first1=D. K. |last1=Chaturvedi |url=https://books.google.com/books?id=Igw6WDcfmp4C&printsec=frontcover#v=onepage&q&f=false |title=Soft Computing: Techniques and Its Applications in Electrical Engineering |publisher=Springer |date=2008 |ref=harv}}
* {{cite web | url=http://researchmathsci.org/apamart/apam-v4n1-3.pdf |date=2013 |title=Fuzzy Graph Theory: A Survey |last1=Sunitha|first1=M.S.|last2=Sunil |first2=Matthew |ref=harv}}
* {{Cite web | url=http://soft-computing.de/def.html | last1=Jin |first1=Yaochu | date=2014| title=Soft Computing Home Page - Short Definition of Soft Computing |ref=harv}}
* {{cite journal |last1=Zadeh |first1=Lotfi A. |url=https://go.galegroup.com/ps/i.do?id=GALE%7CA15061349&sid=googleScholar&v=2.1&it=r&linkaccess=abs&issn=00010782&p=AONE&sw=w |title=Fuzzy Logic, Neural Networks, and Soft Computing| journal= Communications of the ACM|date=March 1994 |volume=37 |number=3| pages =77-84 |ref=harv}}

{{Authority control}}

[[:Category:Scientific modeling]]
[[:Category:Artificial intelligence]]
[[:Category:Semantic Web]]
[[:Category:Soft computing]]