SteveineiterTU opened a new pull request, #1584: URL: https://github.com/apache/systemds/pull/1584
This is WIP. This implements the attention layer. This allows to train RNNs with long term sequences easier using the attention mechanism. A quick reference to what an attention layer is: https://analyticsindiamag.com/a-beginners-guide-to-using-attention-layer-in-neural-networks/ Tasks: - [ ] Add attention.dml to scripts/nn/layers/ with the implementation of the layer. - [ ] Add an AttentionExample.dml file to scripts/nn/examples where the attention layer is used with an lstm-layer to demonstrate that an attention model can be trained and used for predictions. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
