How to set initial weights in MLPClassifier?

Question

I cannot find a way to set the initial weights of the neural network, could someone tell me how please? I am using python package sklearn.neural_network.MLPClassifier.

Answer 1

Solution: A working solution is to inherit from MLPClassifier and override the _init_coef method. In the _init_coef write the code to set the initial weights. Then use the new class "MLPClassifierOverride" as in the example below instead of "MLPClassifier"

# new class
class MLPClassifierOverride(MLPClassifier):
# Overriding _init_coef method
def _init_coef(self, fan_in, fan_out):
    if self.activation == 'logistic':
        init_bound = np.sqrt(2. / (fan_in + fan_out))
    elif self.activation in ('identity', 'tanh', 'relu'):
        init_bound = np.sqrt(6. / (fan_in + fan_out))
    else:
        raise ValueError("Unknown activation function %s" %
                         self.activation)
    coef_init = ### place your initial values for coef_init here

    intercept_init = ### place your initial values for intercept_init here

    return coef_init, intercept_init