search

bst-mug / n2c2

Support code for participation at the 2018 n2c2 Shared-Task Track 1
https://n2c2.dbmi.hms.harvard.edu
Apache License 2.0
6 stars 4 forks source link

Reduce `lstmLayerSize` #99

Closed michelole closed 5 years ago

michelole commented 5 years ago

From 256 to e.g. 128 or 64.

michelole commented 5 years ago

May not be enough to reduce number of features and avoid overfit, we should prioritize #103 .

michelole commented 5 years ago

Experiments showed we are able to reach similar metrics when using a smaller layer size, but models converge linearly faster.

michelole commented 5 years ago

Fixed by 6b541f8488ec5901988e132e27d9d6f60944ab00