🌐 DE
🌙 Dark
Deep Learning Concept
Back
propagation
Run forward to a loss — then watch the gradient flow backward, multiplying local derivatives.
w
0.80
forward →
← backward (gradients)
w
0.80
z = w·x+b
0.80
a = σ(z)
0.69
L = ½(a−y)²
0.05
∂L/∂a
−0.31
∂a/∂z
0.21
∂z/∂w
1.00
∂L/∂w = −0.07
prediction a
0.69
loss L
0.048
gradient ∂L/∂w
−0.066
chain rule: multiply the local derivatives right-to-left to get ∂L/∂w
backward.py