Lukasz Lukasz - 4 months ago 17
Python Question

Matrix Multiplication TypeError

I'm attempting to write a backpropagation algorithm and I'm encountering an error when attempting to perform a matrix multiplication.

I've created the following simple example to work with

# necessary functions for this example
def sigmoid(z):
return 1.0/(1.0+np.exp(-z))

def prime(z):
return sigmoid(z) * (1-sigmoid(z))

def cost_derivative(output_activations, y):
return (output_activations-y)

# Mock weight and bias matrices
weights = [np.array([[ 1, 0, 2],
[2, -1, 0],
[4, -1, 0],
[1, 3, -2],
[0, 0, -1]]),
np.array([[2, 0, -1, -1, 2],
[-3, 2, 0, 1, -1]])]

biases = [np.array([-1, 2, 0, 0, 4]), np.array([-2, 1])]

# The mock training example
q = [(np.array([1, -2, 3]), np.array([0])),
(np.array([2, -3, 5]), np.array([1])),
(np.array([3, 6, -1]), np.array([1])),
(np.array([4, -1, -1]), np.array([0]))]

for x, y in q:
activation = x
activations = [x]
zs = []
for w, b in zip(weights, biases):
z = np.dot(w, activation) + b
zs.append(z)
activation = sigmoid(z)
activations.append(activation)

delta = cost_derivative(activations[-1], y) * prime(zs[-1])
print(np.dot(np.transpose(weights[-1])), delta)


I get the following error:

TypeError: Required argument 'b' (pos 2) not found


I've printed the outputs of both the
weights
transposed which is a 5x2 matrix and
delta
is a 2x1. The outputs are:

np.transpose(weights[-1]) = [[ 2 -3]
[ 0 2]
[-1 0]
[-1 1]
[ 2 -1]]


and

delta = [-0.14342712 -0.03761959]


so the multiplication should work and produce a 5x1 matrix

Answer

There is a misplaced parenthesis on your last line. It should be

print(np.dot(np.transpose(weights[-1]), delta))

instead of

print(np.dot(np.transpose(weights[-1])), delta)
Comments