View source on GitHub
|
Loss functions for neural networks.
Functions
kl_divergence_exact(...): Exact KL Divergence.
kl_divergence_monte_carlo(...): Monte Carlo KL Divergence.
negloglik(...): Negative log-likelihood.
Module: tfp.experimental.nn.losses
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-11-21 UTC.
[null,null,["Last updated 2023-11-21 UTC."],[],[],null,["# Module: tfp.experimental.nn.losses\n\n\u003cbr /\u003e\n\n|--------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/experimental/nn/losses/__init__.py) |\n\nLoss functions for neural networks.\n\nFunctions\n---------\n\n[`compute_extra_loss(...)`](../../../tfp/experimental/nn/losses/compute_extra_loss)\n\n[`kl_divergence_exact(...)`](../../../tfp/experimental/nn/losses/kl_divergence_exact): Exact KL Divergence.\n\n[`kl_divergence_monte_carlo(...)`](../../../tfp/experimental/nn/losses/kl_divergence_monte_carlo): Monte Carlo KL Divergence.\n\n[`negloglik(...)`](../../../tfp/experimental/nn/losses/negloglik): Negative log-likelihood."]]