Скачать или смотреть Perceptron Learning

Perceptron Learning Rule Simulation
===================================
Patterns:
Orange (p1): {1 1 -1} -- Target: 0
Apple (p2): {1 1 1} -- Target: 1

Initial weights: {0.5, -1.0, -0.5}
Initial bias: 0.5

Starting training...

Iteration 1:
Pattern: Orange
Input: {1 -1 -1}
Net input: 2.50
Output: 1, Target: 0
Error: -1
Weights before: {0.5 -1.0 -0.5}
Weights updated!
Weights after: {-0.5 0.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 2:
Pattern: Apple
Input: {1 1 -1}
Net input: -1.50
Output: 0, Target: 1
Error: 1
Weights before: {-0.5 0.0 0.5}
Weights updated!
Weights after: {0.5 1.0 -0.5}
Bias: 0.50
--------------------------------------------------
Iteration 3:
Pattern: Orange
Input: {1 -1 -1}
Net input: 0.50
Output: 1, Target: 0
Error: -1
Weights before: {0.5 1.0 -0.5}
Weights updated!
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 4:
Pattern: Apple
Input: {1 1 -1}
Net input: 0.50
Output: 1, Target: 1
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 5:
Pattern: Orange
Input: {1 -1 -1}
Net input: -3.50
Output: 0, Target: 0
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 6:
Pattern: Apple
Input: {1 1 -1}
Net input: 0.50
Output: 1, Target: 1
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 7:
Pattern: Orange
Input: {1 -1 -1}
Net input: -3.50
Output: 0, Target: 0
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 8:
Pattern: Apple
Input: {1 1 -1}
Net input: 0.50
Output: 1, Target: 1
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 9:
Pattern: Orange
Input: {1 -1 -1}
Net input: -3.50
Output: 0, Target: 0
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------
Iteration 10:
Pattern: Apple
Input: {1 1 -1}
Net input: 0.50
Output: 1, Target: 1
Error: 0
Weights before: {-0.5 2.0 0.5}
Weights after: {-0.5 2.0 0.5}
Bias: -0.50
--------------------------------------------------

Final Results:
==============
Pattern 1 (Orange): Output: 0, Target: 0 ✓
Pattern 2 (Apple): Output: 1, Target: 1 ✓

Process finished with exit code 0