Soft computing: Difference between revisions

Revision as of 12:31, 28 December 2023

Revision as of 08:15, 4 February 2024

Line 1:

'''Soft computing''' is an umbrella term used to describe types of [[algorithm]]s that produce approximate solutions to unsolvable high-level problems in computer science. Typically, traditional hard-computing algorithms heavily rely on concrete data and [[Mathematical Models and Methods in Applied Sciences|mathematical models]] to produce solutions to problems. Soft computing was coined in the late 20th century.<ref>{{Cite journal |last=Zadeh |first=Lotfi A. |date=March 1994 |title=Fuzzy logic, neural networks, and soft computing |url=https://dl.acm.org/doi/10.1145/175247.175255 |journal=Communications of the ACM |language=en |volume=37 |issue=3 |pages=77–84 |doi=10.1145/175247.175255 |issn=0001-0782|doi-access=free }}</ref> During this period, revolutionary research in three fields greatly impacted soft computing. Fuzzy logic is a computational paradigm that entertains the uncertainties in data by using levels of truth rather than rigid 0s and 1s in binary. Next, neural networks which are computational models influenced by human brain functions. Finally, evolutionary computation is a term to describe groups of algorithm that mimic natural processes such as evolution and natural selection.

In the context of [[artificial intelligence]] and [[machine learning]], soft computing provides tools to handle real-world uncertainties. Its methods supplement preexisting methods for better solutions. Today, the combination with artificial intelligence has led to hybrid intelligence systems that merge various computational algorithms. Expanding the applications of artificial intelligence, soft computing leads to robust solutions. Key points include tackling ambiguity, flexible learning, grasping intricate data, real-world applications, and [[Ethics of artificial intelligence|ethical artificial intelligence]].<ref name="Procedia">Ibrahim, Dogan. "An overview of soft computing." Procedia Computer Science 102 (2016): 34-38.</ref><ref name=":1">{{Cite book |last=Kecman |first=Vojislav |url=https://books.google.com/books?id=W5SAhUqBVYoC&lpg=PP21&ots=ev4aPrdxZ4&dq=neural%20networks%20in%20soft%20computing&lr+networks+in+soft+computing&pg=PP1#v=onepage&q=neural%20networks%20in%20soft%20computing&f=false |title=Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models |date=2001 |publisher=MIT Press |isbn=978-0-262-11255-0 |language=en}}</ref>

== History ==

The development of soft computing dates back to the late 20th century. In 1965, [[Lotfi A. Zadeh|Lotfi Zadeh]] introduced fuzz logic, which laid the mathematical groundwork for soft computing. Between the 1960s and 1970s, evolutionary computation, the development of [[Genetic algorithm|genetic algorithms]] that mimicked biological processes, began to emerge. These models carved the path for models to start handling uncertainty. Although neural network research began in the 1940s and 1950s, there was a new demand for research in the 1980s. Researchers invested time to develop models for [[pattern recognition]]. Between the 1980s and 1990s, hybrid intelligence systems merged fuzz logic, neural networks, and evolutionary computation that solved complicated problems quickly. From the 1990s to the present day, Models have been instrumental and affect multiple fields handling [[big data]], including engineering, medicine, social sciences, and finance.<ref>Chaturvedi, Devendra K. "Soft computing." Studies in Computational intelligence 103 (2008): 509-612.</ref><ref name=":0">{{Cite book |lastlast1=Ram |firstfirst1=Mangey |url=https://books.google.com/books?id=qjL3DwAAQBAJ&lpg=PA57&ots=veaMI4lCLY&dq=history%20of%20soft%20computing&lr&pg=PA74#v=onepage&q&f=false |title=Advanced Mathematical Techniques in Engineering Sciences |last2=Davim |first2=J. Paulo |date=2018-05-04 |publisher=CRC Press |isbn=978-1-351-37189-6 |language=en}}</ref>

== Computational techniques ==

Line 22:

Through training, the network handles input and output data streams and adjusts parameters according to the provided information. Neural networks help make soft computing extraordinarily flexible and capable of handling high-level problems.

In soft computing, neural networks aid in pattern recognition, predictive modeling, and data analysis. They are also used in [[image recognition]], [[natural language processing]], [[speech recognition]], and [[System|systems]].<ref name=":1" /><ref name=":3">{{Cite web |title=IEEE Xplore Full-Text PDF: |url=https://ieeexplore.ieee.org/stampdocument/stamp.jsp?tp=&arnumber=8859190 |access-date=2023-11-11 |website=ieeexplore.ieee.org}}</ref>

=== Evolutionary computation ===

Line 32:

=== Hybrid intelligence systems ===

Hybrid intelligence systems combine the strengths of soft computing components to create integrated computational models. Artificial techniques such as fuzzy logic, neural networks, and evolutionary computation combine to solve problems efficiently. These systems improve judgment, [[troubleshooting]], and [[data analysis]]. Hybrid intelligence systems help overcome the limitations of individual AI approaches to improve performance, accuracy, and adaptability to address [[Dynamic problem (algorithms)|dynamic problems]]. It advances soft computing capabilities in data analysis, pattern recognition, and systems.<ref name=":4">{{Cite book |last=Medsker |first=Larry R. |url=https://books.google.com/books?id=EXngBwAAQBAJ&lpgq=PR13&ots=GgqzFWNqj0&dq=hybrid%20intelligent%20system&lrevolutionary&pg=PR13#v=snippet&q=evolutionary&f=false |title=Hybrid Intelligent Systems |date=2012-12-06 |publisher=Springer Science & Business Media |isbn=978-1-4615-2353-6 |language=en}}</ref>

== Applications ==