This document provides an overview of neural networks, including their basic components and types. It discusses neurons, activation functions, and different neural network architectures like feedforward and feedback networks. It also covers supervised, unsupervised, and reinforcement learning methods. Applications of neural networks are described along with their advantages in learning from experience and dealing with incomplete information, and disadvantages like long training times.

1. Adeel Qayyum
Arsalan Ali
Sulman Ahmed

2. Contents
.Introduction to Neural Network
.Neurons
.Activation Function
.Types of Neural Network
.Learning In Neural Networks
.Application of Neural Network
.Advantages of Neural Network
.Disadvantages Of Neural
Network

3. Neural Networks
• A method of computing, based on the
interaction of multiple connected
processing elements.
• A powerful technique to solve many real
world problems.
• The ability to learn from experience in
order to improve their performance.
• Ability to deal with incomplete
information

4. • Biological approach to AI
• Developed in 1943
• Comprised of one or more
layers of neurons
• Several types, we’ll focus on
feed-forward and feedback
networks
Basics Of Neural Network

5. Neurons
Biological
Artificial

6. NeuralNetwork Neurons
• Receives n-inputs
• Multiplies each
input by its
weight
• Applies
activation
function to the
sum of results
• Outputs result

7. ActivationFunctions
• Controls when
unit is “active”
or “inactive”
• Threshold
function outputs
1 when input is
positive and 0
otherwise
• Sigmoid function
= 1 / (1 + e-x)

8. Neural Network types can be classified based on following
attributes:
•Connection Type
- Static (feed forward)
- Dynamic (feedback)
• Topology
- Single layer
- Multilayer
- Recurrent
• Learning Methods
- Supervised
- Unsupervised
- Reinforcement
Types of Neural Networks

9. Classification Based On Connection Types
•Static(Feedforward)
(unit delay operator z-1 implies
dynamic system)
Classification Based On Topology
•Dynamic(Feedback)
•Single layer • Multilayer •Recurrent

10. Classification Based On Learning Method
• Supervised
• Unsupervised
• Reinforcement
Supervised learning
• Each training pattern: input + desired
output
• At each presentation: adapt weights
• After many epochs convergence to a
local minimum

11. Unsupervised Learning
• No help from the outside
• No training data, no information
available on the desired output
• Learning by doing
• Used to pick out structure in the
input:
•Clustering
•Reduction of dimensionality 
compression
• Example: Kohonen’s Learning Law

12. Reinforcement learning
• Teacher: training data
• The teacher scores the performance of the
training examples
• Use performance score to shuffle weights
‘randomly’
• Relatively slow learning due to
‘randomness’

13. Architecture Of Neural Networks
FEED –FORWARD NETWORKS :-
 Allow signals to travel one way only ; from input
to output .
 No feedback (loops) i.e. the output of any layer
does not affect that same layer.
 Feed-forward ANNs tend to be straight forward
networks that associate inputs with outputs.
 extensively used in pattern recognition .

14. FEED-FORWARD NETWORK

15. FEEDBACK NETWORKS :-
 can have signals traveling in both directions by
introducing loops in the network.
 Feedback networks are dynamic; their 'state'
is changing continuously until they reach an
equilibrium point.
 They remain at the equilibrium point until the
input changes and a new equilibrium needs to be
found .
 also referred to as interactive or recurrent .

16. Neural networks versus conventional computers
COMPUTERS
Algorithmic approach
They are necessarily programmed
Work on predefined set
of instructions
Operations are predictable
ANN
Learning approach
Not programmed for specific
tasks
 Used in decision making
 Operation is unpredictable

17. • Pattern recognition
• Investment analysis
• Control systems &
monitoring
• Mobile computing
• Marketing and financial
applications
• Forecasting – sales, market
research, meteorology
Neural Network Applications

18. Advantages:
•A neural network can perform tasks that a
linear program can not.
•When an element of the neural network
fails, it can continue without any problem
by their parallel nature.
•A neural network learns and does not need
to be reprogrammed.
•It can be implemented in any application.
•It can be implemented without any problem

19. Disadvantages:
•The neural network needs training
to operate.
•The architecture of a neural
network is different from the
architecture of microprocessors
therefore needs to be emulated.
•Requires high processing time for
large neural networks.

20. Conclusions
• Neural networks provide ability to
provide more human-like AI
• Takes rough approximation and
hard-coded reactions out of AI
design (i.e. Rules and FSMs)
• Still require a lot of fine-tuning
during development

21. References
• Neural Networks, Fuzzy Logic, and Genetic
Algorithm ( synthesis and Application)
S.Rajasekaran, G.A. Vijayalakshmi Pai, PHI
• Neuro Fuzzy and Soft Computing, J. S. R.
JANG,C.T. Sun, E. Mitzutani, PHI
• Neural Netware, a tutorial on neural networks
• Sweetser, Penny. “Strategic Decision-Making with
Neural Networks and Influence Maps”, AI Game
Programming Wisdom 2, Section 7.7 (439 – 46)
• Russell, Stuart and Norvig, Peter. Artificial
Intelligence: A Modern Approach, Section 20.5
(736 – 48)