Last active
February 26, 2020 11:36
-
-
Save lucasastorian/e483fc459cb9526c9853826191417970 to your computer and use it in GitHub Desktop.
A Self-Normalizing Denoising Autoencoder Architecture
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| input_nodes = 350 | |
| code_nodes = 1500 | |
| hidden_nodes = 1500 | |
| dropout_rate = 0.25 | |
| input_layer = layers.Input(shape=(input_nodes,)) | |
| hidden_1 = layers.Dense(hidden_nodes, activation='selu', kernel_initializer='lecun_normal')(input_layer) | |
| dropout_1 = layers.AlphaDropout(dropout_rate)(hidden_1) | |
| code_layer = layers.Dense(code_nodes, activation='selu', kernel_initializer='lecun_normal')(dropout_1) | |
| dropout_2 = layers.AlphaDropout(dropout_rate)(code_layer) | |
| hidden_2 = layers.Dense(hidden_nodes, activation='selu', kernel_initializer='lecun_normal')(dropout_2) | |
| dropout_3 = layers.AlphaDropout(dropout_rate)(hidden_2) | |
| output_layer = layers.Dense(input_nodes, activation='sigmoid', kernel_initializer='lecun_normal')(dropout_3) | |
| self_normalizing_denoising_autoencoder = models.Model(input_layer, output_layer) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment