accelbrainbase.regularizatabledata package

Subpackages

• accelbrainbase.regularizatabledata._mxnet package
  • Submodules
  • accelbrainbase.regularizatabledata._mxnet.constrain_weights module
  • Module contents

Submodules

accelbrainbase.regularizatabledata.constrain_weights module

class accelbrainbase.regularizatabledata.constrain_weights.ConstrainWeights(weight_limit=0.9)

Bases: accelbrainbase.regularizatable_data.RegularizatableData

Regularization for weights matrix to repeat multiplying the weights matrix and 0.9 until $sum_{j=0}^{n}w_{ji}^2 < weight_limit$.

References

• Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958.
• Zaremba, W., Sutskever, I., & Vinyals, O. (2014). Recurrent neural network regularization. arXiv preprint arXiv:1409.2329.

constrain_weight(weight_arr)

get_weight_limit()

getter

regularize(params_dict)

Regularize parameters.

Parameters:params_dict – is-a mxnet.gluon.ParameterDict. Returns:mxnet.gluon.ParameterDict

set_weight_limit(value)

setter

weight_limit

getter

Module contents