Backpropagation p Ahmed Elngar

1. Lecture – 07
Introduction to soft computing
Dr. Ahmed Elngar
Faculty of Computers and Artificial Intelligence
Beni-Suef University
1
Dr. Ahmed Elngar
12/10/2022

2. Course Syllabus
2
12/10/2022

3. 3
12/10/2022
ANN (artificial neural network)

4. 4
12/10/2022
Network structure
Backpropagation Networks

5. 5
12/10/2022
Backpropagation Networks
Introduction to Backpropagation
- In 1969 a method for learning in multi-layer network, Backpropagation, was invented by
Bryson and Ho.
- The Backpropagation algorithm is a sensible approach for dividing the contribution of
each weight.
- Works basically the same as perceptron

6. 6
12/10/2022
Backpropagation Networks

7. 7
12/10/2022
Backpropagation Networks
Backpropagation Learning Principles: Hidden
Layers and Gradients
There are two differences in the updating rule :
1) The activation of the hidden unit is used instead of the
input value.
2) The rule contains a term for the gradient of the activation
function.

8. 8
12/10/2022
Backpropagation Networks

9. 9
12/10/2022
Backpropagation Networks

10. 10
12/10/2022
Backpropagation Networks

11. 11
12/10/2022
Backpropagation Networks

12. 12
12/10/2022
Backpropagation Networks
Backpropagation Algorithm

13. 13
12/10/2022
Backpropagation Networks

14. 14
12/10/2022
Backpropagation Networks

15. 15
12/10/2022
Backpropagation Networks
How many hidden layers
• Usually just one (i.e., a 2-layer net)
• How many hidden units in the layer?
Too few ==> can’t learn
Too many ==> poor generalization

16. 16
12/10/2022
Backpropagation Networks
A Step by Step Backpropagation Example –
Matt Mazur

17. 17
12/10/2022
Backpropagation Networks
Advantages, limitations

18. 18
12/10/2022
Backpropagation Networks
Advantages, limitations

19. Aim of our Research Group:
19
The aim of our Scientific Innovation research Group
(SIRG) to evaluate the IOT performance by propose a
secure architecture for the IoT security issues for
Education.
12/10/2022

20. Thanks and Acknowledgement
Thank you
20
12/10/2022