pydbm.nn.simpleautoencoder package

Submodules

pydbm.nn.simpleautoencoder.contractive_auto_encoder module

class pydbm.nn.simpleautoencoder.contractive_auto_encoder.ContractiveAutoEncoder

Bases: pydbm.nn.simple_auto_encoder.SimpleAutoEncoder

Contractive Auto-Encoder.

References

  • Kamyshanska, H., & Memisevic, R. (2014). The potential energy of an autoencoder. IEEE transactions on pattern analysis and machine intelligence, 37(6), 1261-1273.
  • Rifai, S., Vincent, P., Muller, X., Glorot, X., & Bengio, Y. (2011, June). Contractive auto-encoders: Explicit invariance during feature extraction. In Proceedings of the 28th International Conference on International Conference on Machine Learning (pp. 833-840). Omnipress.
  • Rifai, S., Mesnil, G., Vincent, P., Muller, X., Bengio, Y., Dauphin, Y., & Glorot, X. (2011, September). Higher order contractive auto-encoder. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 645-660). Springer, Berlin, Heidelberg.
forward_propagation

Forward propagation in NN.

Parameters:observed_arr – np.ndarray of image file array.
Returns:Propagated np.ndarray.
get_penalty_lambda

getter for Positive hyperparameter that controls the strength of the regularization.

penalty_lambda

getter for Positive hyperparameter that controls the strength of the regularization.

set_penalty_lambda

setter for Positive hyperparameter that controls the strength of the regularization.

pydbm.nn.simpleautoencoder.ladder_networks module

class pydbm.nn.simpleautoencoder.ladder_networks.LadderNetworks

Bases: pydbm.nn.simple_auto_encoder.SimpleAutoEncoder

Ladder Networks.

References

  • Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007). Greedy layer-wise training of deep networks. In Advances in neural information processing systems (pp. 153-160).
  • Erhan, D., Bengio, Y., Courville, A., Manzagol, P. A., Vincent, P., & Bengio, S. (2010). Why does unsupervised pre-training help deep learning?. Journal of Machine Learning Research, 11(Feb), 625-660.
  • Erhan, D., Courville, A., & Bengio, Y. (2010). Understanding representations learned in deep architectures. Department dInformatique et Recherche Operationnelle, University of Montreal, QC, Canada, Tech. Rep, 1355, 1.
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning (adaptive computation and machine learning series). Adaptive Computation and Machine Learning series, 800.
  • Rasmus, A., Berglund, M., Honkala, M., Valpola, H., & Raiko, T. (2015). Semi-supervised learning with ladder networks. In Advances in neural information processing systems (pp. 3546-3554).
  • Valpola, H. (2015). From neural PCA to deep unsupervised learning. In Advances in Independent Component Analysis and Learning Machines (pp. 143-171). Academic Press.
alpha_loss_arr

getter

back_propagation

Back propagation in NN.

Parameters:Delta. –
Returns.
Delta.
compute_alpha_loss

Compute denoising loss weighted alpha.

Returns:loss.
compute_mu_loss

Compute mu loss weighted mu.

Returns:loss.
compute_sigma_loss

Compute sigma loss weighted sigma.

Returns:loss.
forward_propagation

Forward propagation in NN.

Parameters:observed_arr – np.ndarray of image file array.
Returns:Propagated np.ndarray.
get_alpha_loss_arr

getter

get_mu_loss_arr

getter

get_sigma_loss_arr

getter

learn

Learn.

Parameters:
  • observed_arr – np.ndarray of observed data points.
  • target_arr – np.ndarray of labeled data. If None, the function of this NN model is equivalent to Convolutional Auto-Encoder.
mu_loss_arr

getter

set_readonly

setter

sigma_loss_arr

getter

pydbm.nn.simpleautoencoder.repelling_auto_encoder module

class pydbm.nn.simpleautoencoder.repelling_auto_encoder.RepellingAutoEncoder

Bases: pydbm.nn.simple_auto_encoder.SimpleAutoEncoder

Repelling Auto-Encoder.

References

  • Zhao, J., Mathieu, M., & LeCun, Y. (2016). Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126.
back_propagation

Back propagation in NN.

Parameters:Delta. –
Returns.
Delta.
forward_propagation

Forward propagation in NN.

Parameters:observed_arr – np.ndarray of observed data points.
Returns:Propagated np.ndarray.

Module contents