# Suppose total_loss accumulates data loss already:

# L_total = L_data + (lambda/2) * sum(W^2)

​

def l2_penalty_mats(mats):

    return sum(sum(w*w for w in row) for M in mats for row in M)

​

def l2_penalty_vecs(vecs):

    return sum(w*w for v in vecs for w in v) if vecs and isinstance(vecs[0], list) else sum(w*w for w in vecs)

​

# Example inside training after accumulating gradients:

lam = 1e-3

# add penalty to total_loss (W1,W2 shown)

total_loss += 0.5 * lam * (l2_penalty_mats([W1]) + sum(w*w for w in W2))

​

# and when updating grads, add lam * W terms (weight decay)

for j in range(hidden):

    for i in range(input_dim):

        dW1[j][i] += lam * W1[j][i]

for j in range(hidden):

    dW2[j] += lam * W2[j]