RandomNormal

class ampligraph.latent_features.RandomNormal(initializer_params={}, verbose=True, seed=0)

Initializes from a normal distribution with specified mean and std

\[\mathcal{N} (\mu, \sigma)\]

Methods

__init__([initializer_params, verbose, seed]) Initialize the Random Normal initialization strategy
__init__(initializer_params={}, verbose=True, seed=0)

Initialize the Random Normal initialization strategy

Parameters:
  • initializer_params (dict) –

    Consists of key-value pairs. The initializer will check the keys to get the corresponding params:

    • mean: (float). Mean of the weights(default: 0)
    • std: (float): std of the weights (default: 0.05)

    Example: initializer_params={'mean': 0, 'std': 0.01}

  • verbose (bool) – Enable/disable verbose mode
  • seed (int/np.random.RandomState) – random state for random number generator