accelbrainbase.regularizatabledata._mxnet package¶
Submodules¶
accelbrainbase.regularizatabledata._mxnet.constrain_weights module¶
-
class
accelbrainbase.regularizatabledata._mxnet.constrain_weights.ConstrainWeights(weight_limit=0.9)¶ Bases:
accelbrainbase.regularizatabledata.constrain_weights.ConstrainWeightsRegularization 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)¶