weight_update_BCE.py

def update_weights_BCE(m1, m2, b, X1, X2, Y, learning_rate):
    m1_deriv = 0
    m2_deriv = 0
    b_deriv = 0
    N = len(X1)
    for i in range(N):
        s = 1 / (1 / (1 + math.exp(-m1*X1[i] - m2*X2[i] - b)))
        
        # Calculate partial derivatives
        m1_deriv += -X1[i] * (s - Y[i])
        m2_deriv += -X2[i] * (s - Y[i])
        b_deriv += -(s - Y[i])

    # We subtract because the derivatives point in direction of steepest ascent
    m1 -= (m1_deriv / float(N)) * learning_rate
    m2 -= (m2_deriv / float(N)) * learning_rate
    b -= (b_deriv / float(N)) * learning_rate

    return m1, m2, b

Is line no 7 right for sigmoid function? I think you inverted twice.