AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Breaking the Activation Function Bottleneck through Adaptive Parameterization

Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use adaptive parameterization with SVALogistic Regression on MNIST · MNIST testaccuracy: 92.14% -> 93.86%Improved
Use 3-layer SVA instead of a 3-layer feed-forward networkFeed-forward model · MNIST testaccuracy: 97.01% -> 97.65%Improved
Use recurrent adaptive parameterizationLSTM on Penn Treebank · Penn Treebank testperplexity: 68.9 -> 55.3Improved
Use recurrent adaptive parameterizationAWD-LSTM on Penn Treebank · Penn Treebank testperplexity: 57.3 -> 55.3Improved
Use recurrent adaptive parameterizationAWD-LSTM on WikiText-2 · WikiText-2 testperplexity: 65.8 -> 64.5Improved
Add recurrent adaptation instead of feed-forward adaptation (ablation)aLSTM with output adaptation · Penn Treebank testperplexity: 63.1 -> 58.2Improved
Add recurrent adaptation instead of feed-forward adaptation (ablation)aLSTM with IO adaptation · Penn Treebank testperplexity: 59.1 -> 56.9Improved
Use IO adaptation instead of output adaptation (ablation)aLSTM with feed-forward adaptation · Penn Treebank testperplexity: 63.1 -> 59.1Improved
Use IO adaptation instead of output adaptation (ablation)aLSTM with recurrent adaptation · Penn Treebank testperplexity: 58.2 -> 56.9Improved
Use LSTM-RHN adaptation instead of LSTM adaptation (ablation)aLSTM with output adaptation · Penn Treebank testperplexity: 58.2 -> 57.3Improved
Use LSTM-RHN adaptation instead of LSTM adaptation (ablation)aLSTM with IO adaptation · Penn Treebank testperplexity: 56.9 -> 56.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy