Instructions:
• Set input values and target output
• Adjust learning rate to control step size
• Click "Step Optimization" to update weights
• Hover over table entries to highlight connections
• Watch loss decrease over time
Network: 2 inputs → 3 hidden (ReLU) → 1 output (linear)
Learning: MSE loss minimized via gradient descent
Input
1.00
0.50
Hidden
0.00
0.00
0.80
Output
0.08
Network Parameters
Weights
Input → Hidden Weights
From I1
From I2
Hidden → Output
→ H1:
-0.792
→ H2:
0.130
→ H3:
0.392
→ H1:
0.677
→ H2:
-0.792
→ H3:
0.823
H1 →:
0.946
H2 →:
0.316
H3 →:
0.099
Gradients
Input → Hidden Gradients
From I1
From I2
Hidden → Output
→ H1:
0.000
→ H2:
0.000
→ H3:
0.000
→ H1:
0.000
→ H2:
0.000
→ H3:
0.000
H1 →:
0.000
H2 →:
0.000
H3 →:
0.000