Hacker News new | ask | show | jobs
by jacek 3470 days ago
That's true, according to the paper improvement over MLP is negligible. It looks like the model is very small and that might be a reason for relatively low performance.
1 comments

The performance of multilayer perceptrons and linear models is significant. The paper additionally allows the MLP and linear models to "cheat" by giving them heavily hand-engineered features incorporating extensive prior knowledge. Even with this benefit, the LSTM outperforms the baselines, but the improvement is considerably smaller.
The performance improvement over