Download presentation
Presentation is loading. Please wait.
1
An Illustrative Example
2
Apple/Banana Sorter
3
Prototype Vectors Measurement Vector Prototype Banana Prototype Apple
Shape: {1 : round ; -1 : eliptical} Texture: {1 : smooth ; -1 : rough} Weight: {1 : > 1 lb. ; -1 : < 1 lb.}
4
Perceptron
5
Two-Input Case Decision Boundary
6
Apple/Banana Example The decision boundary should
separate the prototype vectors. The weight vector should be orthogonal to the decision boundary, and should point in the direction of the vector which should produce an output of 1. The bias determines the position of the boundary
7
Testing the Network Banana: Apple: “Rough” Banana:
9
Hamming Network
10
For Banana/Apple Recognition
Feedforward Layer For Banana/Apple Recognition
11
Recurrent Layer
12
Hamming Operation First Layer Input (Rough Banana)
13
Hamming Operation Second Layer
14
Hopfield Network
15
Apple/Banana Problem Test: “Rough” Banana (Banana)
16
Summary Perceptron Hamming Network Hopfield Network
Feedforward Network Linear Decision Boundary One Neuron for Each Decision Hamming Network Competitive Network First Layer – Pattern Matching (Inner Product) Second Layer – Competition (Winner-Take-All) # Neurons = # Prototype Patterns Hopfield Network Dynamic Associative Memory Network Network Output Converges to a Prototype Pattern # Neurons = # Elements in each Prototype Pattern
17
The End of Chapter III
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.