Soft Computing

What is Soft Computing?

Soft computing differs from conventional(hard computing) in that,

unlike hard computing, it is tolerant of imprecision, uncertainty,
partial truth, and approximations. In effect, the role model for soft
computing is the human mind.
 Soft Computing Hard Computing

● Soft Computing is liberal of inexactness, ● Hard computing needs a exactly state

uncertainty, partial truth and analytic model.
approximation.

● Soft Computing relies on formal logic ● Hard computing relies on binary logic and
and probabilistic reasoning. crisp system.

● Soft computing works on ambiguous and ● Hard computing works on exact data.
noisy data.

● Soft computing can perform parallel ● Hard computing performs sequential

computations. computations.

● Soft computing produces approximate ● Hard computing produces precise results.

results.

● Soft computing will emerge its own ● Hard computing requires programs to be
programs. written.
Techniques of Soft Computing

● Fuzzy logic
● Genetic algorithms
● Artificial neural networks
● Machine learning
● Expert systems
Unique Property of Soft Computing

● Learning from Experimental Data

● Soft computing techniques derive their power of generalization
from approximating or interpolating to produce outputs from
previously unseen inputs by using outputs from previous learned
inputs
Applications Of Soft Computing

● Handwriting Recognition ● Soft Computing to Power

● Image Processing and Data Systems
Compression ● Neuro Fuzzy systems
● Automotive Systems and ● Fuzzy Logic Control
Manufacturing ● Machine Learning
● Soft Computing to Applications
Architecture ● Speech and Vision
● Decision-support Systems Recognition Systems
● Process Control and So On
Classic Example
Neural Networks

● Neural networks are those information processing systems, which are constructed and
implemented to model the human brain.

● The main objective of the neural network research is to develop a computational device
for modeling the brain to perform various computational tasks at a faster rate than the
traditional systems.

● Artificial neural networks perform various tasks such as pattern matching and
classification, Optimization function, approximation, vector quantization and data
clustering.
Artificial Neural Network
● An artificial neural network (ANN) may be defined as an information processing model
that is inspired by the way biological nervous systems, such as the brain, process
information.

● ANN is composed of a large number of highly interconnected processing elements

(neurons) working in unison to solve specific problems.

● Artificial neural networks, like people, learn by example. An ANN is configured for a
specific application, such as pattern recognition or data classification through a learning
process.
Advantages of Neural Networks
1. Adaptive learning: An ANN is endowed with the ability to learn how to do tasks based on
the data given for training or initial experience.
2. Self organization: An ANN can create its own organization or representation of the
information it receives during learning time.
3. Real-time operation: ANN computations may be carried out in parallel. Special hardware
devices are being designed and manufactured to take advantage of this capability of
ANNs.
4. Fault tolerance via redundant information coding. Partial destruction of a neural
network leads to the corresponding degradation of performance. However, some network
capabilities may be retained even after major damage.
Application Scope of Neural Networks
● Air traffic control could be automated with the location, altitude, direction and speed
of each radar blip taken as input to the network. The output would be the air traffic
controller's instruction in response to each blip.
● Appraisal and valuation of property, buildings, automobiles, machinery, etc. should
be an easy task for a neural network.
● Employee hiring could be optimized if the neural networks were able to predict which
job applicant would show the best job performance.
● Fraud detection regarding credit cards, insurance or £aXes could be automated using
a neural network analysis of past incidents.
● Handwriting and typewriting could be recognized by imposing a grid over the
writing, then each square of the grid becomes an input to the neural network. This is
called "Optical Character Recognition."
● Medical diagnosis is an ideal application for neural networks.
Architecture of a simple artificial neuron net

● Each neuron has an internal state of its own.

This internal state is called the activation or
activity level of neuron, which is the function of
the inputs the neuron receives.

● The activation signal of a neuron is transmitted

to other neurons. Remember a neuron can send
only one signal at a time, which can be
transmitted to several other neurons.
Biological Neural Network
Biological Neural Network
The biological neuron consists of three main pans:

1. Soma or cell body - where the cell nucleus is located.

2. Dendrites - where the nerve is connected to the cell body.

3. Axon - which carries the impulses of the neuron

Mathematical model of artificial neuron
Brain vs. Computer
Characteristics Artificial Neural Network Biological(Real) Neural Network

Speed Faster in processing information. Slower in processing information.

Response time is in nanoseconds. The response time is in milliseconds.

Processing Serial processing. More faster Massively parallel processing.

Size & Complexity The size and complexity of an Highly complex and dense network
ANN is based on the chosen of interconnected neurons containing
application and the network neurons of the order of 1011 with 1015
designer. of interconnections.

Control Mechanism There is a control unit for No specific control mechanism

controlling computing activities external to the computing task.
Characteristics Artificial Neural Network Biological(Real) Neural Network

Storage Information storage is New information can be added in the

capacity(memory) replaceable means new data can interconnections by adjusting the
be added by deleting an old one. strength without destroying the older
information.

Fault tolerance Fault intolerant. Information Biological neurons can accept

once corrupted cannot be redundancies, which is not possible
retrieved in case of failure of the in artificial neurons. Even when
system. some cells die, the human nervous
system appears to be performing
with the same efficiency.
Characteristics of ANN

● It is a neurally implemented mathematical model.

● There exists a large no. of highly interconnected processing elements called neurons in an
ANN.
● The interconnections with their weighted linkages hold the informative knowledge.
● The input signals arrive at the processing elements through connections and connecting
weights.
● The processing elements of the ANN have the ability to learn, recall and generalize from the
given data by suitable assignment or adjustment of weights.
● The computational power can be demonstrated only by the collective behavior of neurons,
and it should be noted that no single neuron carries specific information.
Basic Models of Artificial Neural Network

The models of ANN are specified by the three basic entities namely:

● the model's synaptic interconnections

● the training or learning rules adopted for updating and adjusting the
connection weights
● their activation functions.
Connections
The arrangement of neurons to form layers and the connection panem
formed within and between layers is called the network architecture.
There exist five basic types of neuron connection architectures:

● Single-layer feed-forward network

● Multilayer feed-forward network
● Single node with its own feedback
● Single-layer recurrent network
● Multilayer recurrent network
Single-layer feed-forward network
Multilayer feed-forward network
Single node with its own feedback
Single-layer recurrent network
Multilayer recurrent network
Learning
The main property of an ANN is its capability to learn. Learning or training is a process by
means of which a neural network adapts itself to a stimulus by making proper adjustments
resulting in the production of desired response. Broadly, there are two kinds of learning in
ANNs:

1. Parameter learning: It updates the connecting weights in a neural net.

2. Structure learning: It focuses on the change in network structure (which includes the number
of processing elements as well as their connection types).