Revision 944073906 of "Draft:Soft computing" on enwiki

{{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}}
}}

==Criticism of computer science==
[[File:Soft Computing pic.jpg|thumb|Soft Computing diagram]]
'''Soft computing''' is an insignificant discipline within Artificial Intelligence which is trying to redefine existing computer science. The mainstream attempt of creating intelligent machines is described with a pejoratively connotation as “hard computing”.<ref>{{cite journal |doi=10.1007/978-3-642-24672-2_1 |year=2011 |publisher=Springer Berlin Heidelberg |pages=3--36 |author=Rudolf Seising and Veronica Sanz |title=From Hard Science and Computing to Soft Science and Computing An Introductory Survey |conference=Soft Computing in Humanities and Social Sciences }}</ref> Soft computing claims to bypass existing bottlenecks in science with a strong bias towards [[semiotics]] <ref>{{cite conference |title=From semiotics to computational semiotics |author=Gudwin, 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) |year=1999 }}</ref><ref>{{cite conference |title=Computing Fuzzy Semantic Granules from Natural Language Texts |author=Rieger, B |conference=Proc. 7th IPMU Conf. |pages=475--479 |year=1998 }}</ref> and imprecise knowledge.<ref>{{cite journal |doi=10.1016/j.procs.2016.09.366 |year=2016 |publisher=Elsevier BV |volume=102 |pages=34--38 |author=Dogan Ibrahim |title=An Overview of Soft Computing |journal=Procedia Computer Science }}</ref> At the same time, it's implied that the normal, so called “hard science” isn't motivated to deal with [[probability]] and with the [[symbol grounding problem]].

In the early 1990s the first papers about soft computing were published by [[Lotfi Zadeh]], which is known as the father of [[Fuzzy logic]]. He improved a range-based logic system into a [[universal science]] which stands in opposition to Artificial Intelligence. Soft computing isn't a positive independent theory about a new sort of neural networks or a certain algorithm to process information but it's a critique on existing artificial Intelligence teaching. According to soft computing [[advocacy group]]s, normal computer science isn't able to analyze cognitive processes <ref>{{cite journal |doi=10.2991/ijcis.2010.3.2.4 |year=2010 |publisher=Atlantis Press |volume=3 |number=2 |pages=160 |author=Rudolf Seising |title=What is Soft Computing? Bridging Gaps for 21st Century Science! |journal=International Journal of Computational Intelligence Systems }}</ref> and its using the wrong sort of [[mathematical statistics]].

There are some research projects ongoing in which the theory of soft computing was demonstrated for practical examples.<ref>{{cite journal |doi=10.1007/s005000000053 |year=2000 |publisher=Springer Science and Business Media LLC |volume=4 |number=4 |pages=238--250 |author=C. Zhou |title=Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot |journal=Soft Computing }}</ref><ref>{{cite journal |doi=10.1109/3477.979962 |year=2002 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=32 |number=1 |pages=77--90 |author=F. Karray and W. Gueaieb and S. Al-Sharhan |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> Neuron [[MOS transistor]]s where build <ref>{{cite conference |title=Soft-computing integrated circuits for intelligent information processing |author=Shibata, Tadashi and Yagi, Masakazu and Adachi, Masayoshi |conference=Proceedings of The Second International Conference on Information Fusion |volume=1 |pages=648--656 |year=1999 }}</ref> and emotional pets <ref>{{cite journal |doi=10.1109/5.949483 |year=2001 |publisher=Institute of Electrical and Electronics Engineers (IEEE) |volume=89 |number=9 |pages=1243--1265 |author=Y. Dote and S.J. Ovaska |title=Industrial applications of soft computing: a review |journal=Proceedings of the IEEE }}</ref> were designed. Most of these make-shift projects are ignored by machine learning experts because the existing mathematical tools for building CPUs and intelligent robots are sufficient to fulfill current and future demands.

Within the history of Artificial Intelligence there is a trend available to include [[linguistics]] and probability theory into existing software frameworks.<ref>{{cite conference |doi=10.1109/ifsa-nafips.2013.6608492 |year=2013 |publisher=IEEE |author=Rudolf Seising and Marco Elio Tabacchi |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 Meeting (IFSA/NAFIPS) }}</ref> The highly successful innovation of [[deep learning]] is based on the idea, that input data is transformed into abstract representation. This development shows, that so called hard science has the right tools to deal with imprecise information and there is no need to introduce fuzzy logic.


==Thinking with approximate models==
Soft computing, as opposed to traditional computing, deals with approximate models and gives solutions to complex real-life problems.{{clarify|date=January 2020}} It was conceived by [[Lotfi Zadeh]], pioneer of a mathematical concept known as [[fuzzy sets]] which led to many new fields such as [[fuzzy control system]]s, fuzzy graph theory<ref> http://researchmathsci.org/apamart/apam-v4n1-3.pdf</ref>, [[fuzzy systems]], and so on.   Zadeh observed that people are good at 'soft' thinking while computers typically are 'hard' thinking.<ref>http://soft-computing.de/def.html</ref>  People use concepts like 'some', 'most', or 'very' rather than 'hard' or precise concepts of 3.5 or 102. People want a 'warm' glass of milk, not one that is 102 degrees. 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 - it cannot easily adapt. 'Soft' computing by contrast embraces chaotic, neural models of computing that are more pliable.  Because there is no known single method that lets us compute like people,  soft computing involves using a combination of methods that each bring something helpful to achieve this goal.

===Introduction===
Soft Computing became a formal area of study in Computer Science in the early 1990s.<ref>Zadeh, Lotfi A., "[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 Fuzzy Logic, Neural Networks, and Soft Computing],"  Communications of the ACM, March 1994, Vol. 37 No. 3, pages 77-84.</ref>{{failedverification|date=January 2020}}  Earlier 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.  Complexity of systems is relative and many conventional mathematical models have been very productive in spite of their complexity.{{cn|date=January 2020}}

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]].<ref>X. S. Yang, Z. H. Cui, R. Xiao, A. Gandomi, M. Karamanoglu, [https://books.google.com/books?id=J0VcBQxtcwsC&printsec=frontcover#v=onepage&q=%22soft%20computing%22&f=false Swarm Intelligence and Bio-Inspired Computation: Theory and Applications], Elsevier, (2013).</ref><ref>D. K. Chaturvedi, "[https://books.google.com/books?id=Igw6WDcfmp4C&printsec=frontcover#v=onepage&q&f=false Soft Computing: Techniques and Its Applications in Electrical Engineering]", Springer, (2008).</ref>

===Components===
Components of soft computing include:
*[[Machine learning]], including:
** [[Neural network]]s (NN)
*** [[Perceptron]]
** [[Support Vector Machine]]s (SVM)
* [[Fuzzy logic]] (FL)
* [[Evolutionary computation]] (EC), including:
** [[Evolutionary algorithm]]s
*** [[Genetic algorithm]]s
*** [[Differential evolution]]
** [[Metaheuristic]] and [[Swarm Intelligence]]
*** [[Ant colony optimization]]
*** [[Particle swarm optimization]]
*** [[Cuckoo Search Algorithm]]
*** [[Weed Optimization Algorithm]]
* Ideas about [[probability]] including:
** [[Bayesian network]]

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 full truth, 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.


==Keypoints==
===Remove from text===
* remaining sections written in natural language can be aggregated into a single section
* section components: bullet points with links to other articles doesn't contains valuable information
* section external links: URL to external websites are not referenced in the text -> can be deleted
===Overview===
* opposition is "hard computing"
* is part of Computational Semiotics [6]
* is related to cybernetics 
* “Hard science” is dominated by mathematical precision [9], “hard science” has to do with psychology and humanities
* exact models are numerical, approximate models are imprecise [10]
* is a general system theory [5] about anything and nothing
* Cognitive processes are analyzed with Computational Semiotics [8] 

===details===
* fuzzy logic & soft computing
* soft computing: fuzzy logic, neural networks, genetic algorithm and probabilistic robotics. 
* Soft computing = Computational Intelligence
* term was introduced in the 1990s [1], Term was introduced in 1991 by Lotfi A Zadeh
* application: emotional pet [2], biped walking [3], self-tuning controller [4]
* can be implemented in hardware, for example with the Neuron MOS Transistor [7]
* can be reduced to neural networks -> no it's wrong because neural network are numerical models
* machine learning is oriented on statistics, while soft computing is focused on linguistics and fuzzy logic
* "soft computing" vs "artificial intelligence": shared similarity are neural networks

==References==
{{reflist}}

==External links==
* [http://www.softcomputing.es EUROPEAN CENTRE FOR SOFT COMPUTING]
* [https://web.archive.org/web/20080106133957/http://www.helsinki.fi/~niskanen/bisc.html BISC SIG IN PHILOSOPHY OF SOFT COMPUTING]
* [https://www.cs.upc.edu/~websoco/ SOCO: UPC Group on Soft Computing Systems]
* http://www.soft-computing.de/def.html
* https://web.archive.org/web/20160310135547/http://dspace.nitrkl.ac.in:8080/dspace/bitstream/2080/1136/1/subudhi.pdf

{{Authority control}}

<!-- [[Category:Scientific modeling]]
[[Category:Artificial intelligence]]
[[Category:Semantic Web]]
[[Category:Soft computing]]
 -->