7. 2.1 FEED-FORWARD (ASSOCIATIVE)
NETWORKS
Allow signals to travel
one way only; from
input to output.
There is no feedback.
It tend to be straight
forward networks .
8. 2.2 FEEDBACK (AUTO ASSOCIATIVE)
NETWORKS
Signals travelling in
both directions.
It is dynamic.
Their 'state' is
changing continuously.
It is very powerful.
9. 2.3 NETWORK LAYERS.
I. Input: represents the
raw information.
II. Hidden: determined
by the activities of the
input units .
III. Output: depends on
the activity of the
hidden units.
11. 3.1 HOW THE HUMAN BRAIN LEARNS?
Neuron collects signals from others through a host
called dendrites.
Neuron sends out spikes of electrical activity
through a long, thin stand known as an axon.
A synapse converts the activity from the axon into
electrical effects that excite activity from the axon in
the connected neurones.
15. 4.1 NEURAL NETWORKS IN BUSINESS
Sales forecasting
Industrial process control
Customer research
Data validation
Risk management
Target marketing
16. 4.2 NEURAL NETWORKS IN MEDICINE
cardiograms
CAT scans
ultrasonic scans, etc…
17. 4.3 NEURAL NETWORKS IN BUSINESS
Marketing
Credit Evaluation
Stock Market
18. OTHER APPLICATIONS
Character Recognition
Image Compression
Food Processing
Signature Analysis
Monitoring
19. 5.ADVANTAGES:
Adapt to unknown situation.
Autonomous learning & generalization.
Robustness: fault tolerance due to network
redundancy.
Noise tolerance
Ease of maintenance
20. 6.DISADVANTAGES:
No exact.
Large complexity of the network structure.
NN needs training to operate.
Requires high processing time for large NN.
NN sometimes become unstable.
21. 7.NEURAL NETWORK IN FUTURE
Robots that can see, feel, and predict the world
around them.
Composition of music.
Handwritten documents to be automatically
transformed into formatted word processing
documents.
Self-diagnosis of medical problems using neural
networks.
22. 8.CONCLUSION:
Their ability to learn by example makes them very
flexible and powerful. There is no need to devise an
algorithm to perform a specific task. There is no
need to understand the internal mechanisms of that
task. They are also very well suited for real time
systems.