Download presentation

Presentation is loading. Please wait.

1
PART 5 Supervised Hebbian Learning

2
Outline Linear Associator The Hebb Rule Pseudoinverse Rule Application

3
Hebb ’ s Postulate “When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A’s efficiency, as one of the cells firing B, is increased.” D. O. Hebb, 1949 A B

4
Linear Associator

5
Hebb Rule(1/2)

6
Hebb Rule(2/2)

7
Batch Operation

8
Performance Analysis(1/2)

9
Performance Analysis(2/2)

10
Example(1/2)

11
Example(2/2)

12
Pseudoinverse Rule(1/2)

13
Pseudoinverse Rule(2/2)

14
Relationship to the Hebb Rule

16
Example

17
Autoassociative Memory

18
Tests 50% Occluded 67% Occluded Noisy Patterns (7 pixels)

19
Variations of Hebbian Learning Basic Rule: Learning Rate: Smoothing: Delta Rule: Unsupervised:

20
Solved Problems

22
Solution:

23
Solved Problems

27
Solution :

28
Solved Problems

35
Solution:

36
Solved Problems

Similar presentations

© 2020 SlidePlayer.com Inc.

All rights reserved.

To make this website work, we log user data and share it with processors. To use this website, you must agree to our Privacy Policy, including cookie policy.

Ads by Google