# Weight gradients show how to adjust connections
print("Weight gradient calculation:")
print("dW2 = a1.T @ dz2 / m")

print(f"a1.T shape: {a1.T.shape}")  # Transposed hidden activations
print(f"dz2 shape: {dz2.shape}")    # Output gradients
print(f"dW2 shape: {(a1.T @ dz2).shape}")  # Weight gradients

# This gives us the gradient for each weight connection
print(f"\nWeight gradients tell us:")
print(f"- Positive gradient: decrease this weight")
print(f"- Negative gradient: increase this weight")
print(f"- Large gradient: this weight has big impact on error")