Open Access
Table 1
Overview of the autoencoder hyperparameters, their values, and their meaning.
| Hyperparameter | Values | Explanation |
|---|---|---|
| Learning rate (LR) | [1e-4, 5e-4, 1e-3] | Controls the step size in gradient descent, determining how quickly the model learns. |
| Embedding dimensions | [8, 16] | The size of the encoded representation in the latent space. |
| Number of layers | [1, 2, 4] | The number of layers in the encoder and decoder subnetworks. |
| Number of attention heads | [8, 16] | Number of different attention mechanisms used in each layer. |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.