Soft Computing
Soft Computing
Soft Computing is an umbrella term to describe types of algorithms that produce approximate solutions to unsolvable high-level problems in the field of computer science. Typically, traditional hard-computing algorithms heavily rely on concrete data and mathematical models in order to produce solutions to problems. The term soft computing was coined in the late 20th century and handles incomplete, obscure problems that handle data and variability. [1]During this time period, revolutionary research in three fields greatly impacted soft computing. Fuzzy logic which is a computational paradigm that allows uncertainties in data to be entertained by using levels of truth rather than rigid 0's and 1's in binary. Next, neural networks which are computational models influenced by human brain functions. Finally, evolutionary computation which are algorithms that mimics natural process such as evolution.
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 powerful solutions. Key points include: tackling ambiguity, flexible learning, grasping intricate data, real-world applications, and ethical artificial intelligence. [2]
History
The development of soft computing dates back to the late 20th century. In 1965, Lotfi Zadeh introduces fuzz logic that laid the mathematical groundwork for soft computing. Between the 1960's and 70's, evolutionary computation, the development of 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 40's and 50's, there was a new demand for neural network research in the 80's. Researchers invested time to develop models for pattern recognition. Between the 80's and 90's, existing models began to merge with genetic algorithms, fuzzy logic, and neural networks to create hybrid-intelligence systems that were better equipped to solve complicated problems. From the 90's to the present day, Models have been instrumental and affect multiple fields handling big data including: engineering, medicine, social sciences, and finance. [3]
Key Components of Soft Computing
Fuzzy Logic
Fuzzy Logic is an aspect of computing that handles approximate reasoning. Typically, binary logic solely allows computers to make decisions on true or false reasons (0's and 1's); however, the introduction of fuzzy logic allows systems to handle the unknowns between 0 and 1.
Unlike classical sets that allow members to either be completely within the set or out, fuzzy sets allow partial membership by incorporating "graduation" between sets. Fuzzy logic operations include negation, conjunction, and disjunction, which allow for the handling of membership between sets of data.
Fuzzy rules are logical statements that map the correlation between input and output parameters. They set the rules needed to linguistically trace variable relationships. They would not be possible without linguistic variables. Representing values that are typically not quantifiable, linguistic variables allow uncertainties to be entertained.[2][4]
Neural Networks
Neural networks are computational models that attempt to mimic the structure and functioning of the human brain. Typically, computers seeks to use binary logic in order to solve problems; however, neural networks attempt to provide solutions for complicated problems by enabling systems to think human-like, which is essential to soft computing.
The structure of neural networks revolve around perceptrons, which are basically artificial neurons, that are structured in layers. Similar to the human brain, these interconnected nodes process information like data using complicated mathematical operations.
Through a process called training, the network handles streams of input and output data and adjusts parameters according to the provided information. This helps soft computing be extremely flexible and handle high level problems.
In soft computing, neural networks aid in pattern recognition, predictive modeling, and data analysis. They are applied in the fields of image recognition, natural language processing, speech recognition, and systems.
Evolutionary Computation
Evolutionary computation is a field in soft computing that uses the principles in natural selection and evolution to solve complicated problems. It promotes the discovery of diverse solutions within a solution space, encouraging near-perfect solutions. It finds the satisfactory solutions by using computational models and types of evolutionary algorithms. Evolutionary computation consists of algorithms that mimic natural selection such as genetic algorithms, genetic programming, and evolutionary programming. These algorithms use crossover, mutation, and selection.
Crossover also known as recombination exchanges data between a pair of nodes to diversify data and handle more outcomes. Mutation is genetic technique that help prevent the premature conclusion to a suboptimal solution by diversifying an entire range of solutions. It helps new optimal solutions in solution sets that help the overall optimization process. Selection is an operator that chooses which solution from a current population is fit enough to transition to the next phase. These drives genetic programming to find optimal solutions by ensuring the survival of only the fittest solutions in a set.
In soft computing, evolutionary computation helps applications of data mining (process of using large sets of data to find patterns), robotics, optimizing, and engineering methods.
Hybrid Intelligence Systems
Hybrid intelligence systems combine the strengths of soft computing components to created integrated computational models. The artificial techniques such as fuzz logic, neural networks, and evolutionary computation combine to solve problems efficiently. These systems are leveraged to 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 problems. It advances soft computing capabilities in data analysis, pattern recognition, and systems.
Applications
Soft computing models are extremely valuable tools that confront complex real-world problems due to their dynamic versatility. They are applicable in numerous industries and research fields:
Soft computing fuzzy logic and neural networks helps for pattern recognition, image processing, and computer vision. Its versatility plays a vital role is natural language processing as it helps decipher human emotions and language. They also aid in data mining and predicative analysis by obtaining priceless insights from enormous datasets. Soft computing helps optimize solutions from energy, financial forecasts, modeling environmental and biological data, and anything that deals or requires models.
Within the medical field, soft computing is revolutionizing the detection of disease, creating plans to treat patients, and models of healthcare.
Challenges and Limitations
(your article name) is... (description)
References
- ^ Zadeh, Lotfi A. (1994-03). "Fuzzy logic, neural networks, and soft computing". Communications of the ACM. 37 (3): 77–84. doi:10.1145/175247.175255. ISSN 0001-0782.
{{cite journal}}: Check date values in:|date=(help) - ^ a b Ibrahim, Dogan. "An overview of soft computing." Procedia Computer Science 102 (2016): 34-38.
- ^ Chaturvedi, Devendra K. "Soft computing." Studies in Computational intelligence 103 (2008): 509-612.
- ^ Trillas, Enric, and Luka Eciolaza. "Fuzzy logic." Springer International Publishing. DOI 10 (2015): 978-3.
External links