tf.keras.activations.elu
Stay organized with collections
Save and categorize content based on your preferences.
Exponential Linear Unit.
tf.keras.activations.elu(
x, alpha=1.0
)
The exponential linear unit (ELU) with alpha > 0 is define as:
x if x > 0- alpha *
exp(x) - 1 if x < 0
ELUs have negative values which pushes the mean of the activations
closer to zero.
Mean activations that are closer to zero enable faster learning as they
bring the gradient closer to the natural gradient.
ELUs saturate to a negative value when the argument gets smaller.
Saturation means a small derivative which decreases the variation
and the information that is propagated to the next layer.
Reference:
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. Some content is licensed under the numpy license.
Last updated 2024-06-07 UTC.
[null,null,["Last updated 2024-06-07 UTC."],[],[],null,["# tf.keras.activations.elu\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/activations/activations.py#L168-L193) |\n\nExponential Linear Unit. \n\n tf.keras.activations.elu(\n x, alpha=1.0\n )\n\nThe exponential linear unit (ELU) with `alpha \u003e 0` is define as:\n\n- `x` if `x \u003e 0`\n- alpha \\* `exp(x) - 1` if `x \u003c 0`\n\nELUs have negative values which pushes the mean of the activations\ncloser to zero.\n\nMean activations that are closer to zero enable faster learning as they\nbring the gradient closer to the natural gradient.\nELUs saturate to a negative value when the argument gets smaller.\nSaturation means a small derivative which decreases the variation\nand the information that is propagated to the next layer.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----|---------------|\n| `x` | Input tensor. |\n\n\u003cbr /\u003e\n\n#### Reference:\n\n- [Clevert et al., 2016](https://arxiv.org/abs/1511.07289)"]]
View source on GitHub