UIT BARKATULLAH , BHOPAL(M.P.
COMPUTER SCIENCE ENGINEERING
7th SEMESTER
CS-708 :- SEMINAR
TOPIC :-SOFT COMPUTING
SUBMITTED TO:- SUBMITTED BY:-
MRS. JAGRITI CHAND NUPUR BOPCHE
INDEX :
-
1. Introduction to Soft Computing
2. Soft v/s Hard computing
3. History of Soft Computing
4. Components of Soft Computing
5. Applications Of Soft Computing
6. Advantages Of Soft Computing
7. Disadvantages Of Soft Computing
8. Recent Developments & Future Trends
9. Conclusion
1. Introduction to Soft Computing
Soft computing is the reverse of hard (conventional) computing.
It refers to a group of computational techniques that are based
on artificial intelligence (AI) and natural selection.
It provides cost-effective solutions to the complex real-life
problems for which hard computing solution does not exist.
Soft Computing solutions are unpredictable , uncertain and
Between 0 and 1.
Example :- string1 = "xyz" and string2 = “xyw”
Q1 : Are string1 & string2 same?
Q2 : How much string1 & string2 same?
2. Soft v/s Hard Computing
3. History of Soft Computing
1. 1950s - Emergence of Cybernetics: Norbert Wiener and Warren McCulloch
-- adaptive and learning systems.
2. 1960s - Fuzzy Logic : Lotfi Zadeh
3. 1970s - Artificial Neural Networks (ANNs):- Frank Rosenblatt -perceptron
4. 1980s - Expert Systems and Genetic Algorithms: John Holland
5. 1990s - Emergence of Soft Computing
The term "soft computing" was coined by Lotfi Zadeh in the early 1990s to describe a unified
approach that combined fuzzy logic, neural networks. and genetic algorithms.
6. 2000s - Integration and Hybridization
7. Recent Years - Machine Learning and
AI Dominance
4. Components of Soft Computing
Components Of Soft Computing
Fuzzy Neural Genetic Swarm
Probabilisti
c
Logic Network Algorithm Intelligence
Reasoning
Fuzzy Logic
Fuzzy logic contains the multiple logical values and these values are the truth
values of a variable or problem between 0 and 1. This concept was introduced
by Lofti Zadeh in 1965 based on the Fuzzy Set Theory. This concept provides
the possibilities which are not given by computers, but similar to the range of
possibilities generated by humans.
It is used to deal with imprecise or uncertain information and is a
mathematical method for representing vagueness and uncertainty in
decision-making.
Neural Networks
Neural networks are computational models inspired by the structure and
functioning of the human brain. They are capable of learning and generalizing
from data, making them suitable for pattern recognition, classification, and
function approximation tasks.
Soft computing emphasizes learning from data and adapting to changing
conditions. Neural networks are capable of learning patterns and
relationships from large datasets, which is essential in soft computing to
make predictions or decisions based on uncertain or incomplete information.
Genetic algorithms
Genetic algorithms simulate the process of natural selection which
means those species who can adapt to changes in their environment
are able to survive and reproduce and go to next generation.
Genetic algorithms have been successfully applied in various soft
computing domains, including parameter optimization in machine
learning algorithms, feature selection, job scheduling, resource
allocation, and evolutionary robotics, among others.
Probabilistic reasoning
Probabilistic reasoning is a way of knowledge
representation where we apply the concept of probability to
indicate the uncertainty in knowledge. In probabilistic
reasoning, we combine probability theory with logic to
handle the uncertainty.
Swarm Intelligence
Swarm intelligence is based on the collective behavior of
decentralized and self-organized systems. Examples include
Ant Colony Optimization and Particle Swarm Optimization,
which mimic the behaviors of ants and swarms of birds,
respectively, to solve optimization problems.
Application Of Soft Computing
1. Pattern Recognition and Image
Processing
2. Natural Language Processing
(NLP)
3. Recommendation Systems:
4. Speech Recognition
5. Autonomous Vehicles and
Robotics
6. Healthcare and Medical
Diagnosis
7. Financial Forecasting and
Trading
Advantages Of Soft Computing
1. Robustness: handle uncertainty, imprecision,
and noise in data, making them ideal for solving
real-world problems.
2. Approximate solutions: provide approximate
solutions to complex problems that are difficult or
impossible to solve exactly.
3. Non-linear problems: fuzzy logic and neural
networks can handle non-linear problems
effectively.
4. Human-like reasoning: mimic human-like
reasoning, which is often more effective in solving
complex problems.
5. Real-time applications provide real-time
solutions to complex problems, making them ideal
for use in real-time applications.
Disadvantages Of Soft Computing
1. Approximate solutions: provide
approximate solutions, which may not
always be accurate.
2. Computationally intensive: unsuitable
for use in some real-time applications.
3. Lack of transparency: making it
difficult to understand how the solution
was arrived at.
4. Difficulty in validation: The
approximation techniques can
sometimes make it difficult to validate
the results, leading to a lack of
confidence in the solution.
5. Complexity: making difficult to
implement them effectively.
Recent Developments & Future Trends
1. Explainable AI (XAI):
How AI models arrive at their decisions
2. Federated Learning:
Soft computing models are trained across decentralized edge devices
while keeping data on the device
3. Edge Computing:
Soft computing models are being deployed on edge devices, such as
smart phones, IoT devices
4. Self-Supervised Learning:
Here models learn from unlabeled data or generate their own labels
5. Robotic Process Automation (RPA):
Fuzzy logic and neural networks, are being used in RPA to automate
repetitive tasks in various industries.
Conclusion
In conclusion, soft computing represents a powerful paradigm in the
world of computing and artificial intelligence.
Its unique ability to handle uncertainty, adapt to dynamic
environments, and model complex real-world problems makes it an
indispensable tool in today's technology-driven landscape.
Thank you for joining me on
this journey through the world
of soft computing.
