言語
English
Bengali
French
Hindi
Italian
Japanese
Korean
Malayalam
Russian
Spanish
Tamil
Turkish
Vietnamese



EffectiveDimension.get_fisher_information

EffectiveDimension.get_fisher_information(gradients, model_outputs)[ソース]

This method computes the average Jacobian for every set of gradients and model output as shown in Abbas et al.

パラメータ:
  • gradients (ndarray) – A numpy array, result of the neural network’s backward pass, of shape (num_input_samples * num_weight_samples, output_size, num_weights).

  • model_outputs (ndarray) – A numpy array, result of the neural networks』 forward pass, of shape (num_input_samples * num_weight_samples, output_size).

戻り値:

A numpy array of shape

(num_input_samples * num_weight_samples, num_weights, num_weights) with the average Jacobian for every set of gradients and model output given.

戻り値の型:

fisher