3 An Illustrative Example 1 3 AppleBanana Sorter
3 An Illustrative Example 1
3 Apple/Banana Sorter 2
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. } 3
3 Perceptron 4
3 Two-Input Case Decision Boundary 5
3 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 6
3 Testing the Network Banana: Apple: “Rough” Banana: 7
3 8
3 Hamming Network 9
3 Feedforward Layer For Banana/Apple Recognition 10
3 Recurrent Layer 11
3 Hamming Operation First Layer Input (Rough Banana) 12
3 Hamming Operation Second Layer 13
3 Hopfield Network 14
3 Apple/Banana Problem Test: “Rough” Banana (Banana) 15
Summary 3 • Perceptron – 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 16
3 The End of Chapter III 17
- Slides: 17