EE6006 - APPLIED SOFT COMPUTING
UNIT I: ARCHITECTURES – ANN
Introduction – Biological neuron – Artificial neuron – Neuron model – Supervised and unsupervised
learning- Single layer – Multi layer feed forward network – Learning algorithm- Back propagation
network.
UNIT II : NEURAL NETWORKS FOR CONTROL
Feedback networks – Discrete time Hopfield networks – Transient response of continuous time system –
Applications of artificial neural network - Process identification – Neuro controller for inverted
pendulum.
UNIT III : FUZZY SYSTEMS
Classical sets – Fuzzy sets – Fuzzy relations – Fuzzification – Defuzzification – Fuzzy rules -
Membership function – Knowledge base – Decision-making logic – Introduction to neuro fuzzy system-
Adaptive fuzzy system.
UNIT IV : APPLICATION OF FUZZY LOGIC SYSTEMS
Fuzzy logic control: Home heating system - liquid level control - aircraft landing- inverted pendulum –
fuzzy PID control, Fuzzy based motor control.
UNIT V : GENETIC ALGORITHMS
Introduction-Gradient Search – Non-gradient search – Genetic Algorithms: binary and real representation
schemes, selection methods, crossover and mutation operators for binary and real coding - constraint
handling methods – applications to economic dispatch and unit commitment problems.
BOOKS
Laurance Fausett, Englewood cliffs, N.J.,
‘Fundamentals of Neural Networks’,Pearson
Education,1992.
Timothy J. Ross, ‘Fuzzy Logic with Engineering
Applications’, Tata McGraw Hill, 1997.
S.N.Sivanandam and S.N.Deepa, Principles of Soft
computing, Wiley India Edition, 2nd Edition, 2013.
INTRODUCTION
VS
SOFT COMPUTING
Idea - To model cognitive behavior of human mind.
Conceptual intelligence in machines
Tolerant of imprecision, uncertainty, partial truth, and
approximation.
Well suited for real world problems where ideal
models are not available.
ELEMENTS OF SOFT COMPUTING
ARTIFICIAL FUZZY
NEURAL LOGIC
NETWORKS SYSTEMS
EVOLUTIONARY
ALGORITHMS
Fundamentals of Neural Networks
What is Neural Network ?
An information processing model that is inspired by the way
biological nervous system such as the brain, process
information.
A neural network is an artificial representation of the human
brain that tries to simulate its learning process.
An artificial neural network (ANN) is often called a "Neural
Network“ or simply Neural Net (NN).
Fundamentals of Neural Networks
ANN is an interconnected group of artificial neurons that
uses a mathematical model for information processing.
An ANN is configured for a specific application through a
learning process.
Why Neural Network?
Neural Networks follow a different paradigm for
computing.
The conventional computers are good for - fast arithmetic
Not so good for - interacting with noisy data or data from
the environment
The neural network systems help where we cannot
formulate an algorithmic solution
Advantages
Adaptive learning – Ability to learn
Self organization – Creates its own
Real time operation
Applications
Medical diagnosis
Recognition of Photos and fingerprints
Speech recognition
Load Forecasting
Weather Forecasting
Appraisal and valuation of property
Machinery control etc.,
Biological Neuron
Terminal Branches
Dendrites
of Axon
Synapse
Nucleus
Axon
Artificial Neuron
Terminal Branches
Dendrites
of Axon
x1
w1
x2
w2
x3 w3
S
Axon
wn
xn
ANN - HISTORY
….
ANN – HISTORY
BASIC MODELS OF ANN
The model's synaptic interconnections
The training or learning rules adopted for updating
and adjusting the connection weights
Their activation functions.
CONNECTIONS
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
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Supervised Learning
Unsupervised Learning
Reinforcement Learning
ACTIVATION FUNCTIONS
Identity function:
Binary Step function:
ACTIVATION FUNCTIONS….
Bipolar Step function:
Sigmoidal functions:
Binary Sigmoid function:
ACTIVATION FUNCTIONS….
Bipolar Sigmoid function:
Ramp function:
TERMINOLOGIES IN ANN
Weights
Bias
Threshold
Learning Rate
Momentum Factor
Vigilance Factor
PERCEPTRON
Perceptron solution [Rosenblatt, 1958]
Weights and thresholds can be determined analytically or by
a learning algorithm
Continuous, bipolar and multiple-valued versions
