AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Sigsoftmax: Reanalysis of the Softmax Bottleneck

Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 20 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
Replace softmax with sigsoftmax3-layer LSTM · PTB test + dynamic eval.perplexity: 50.5±0.5 -> 49.2 ± 0.4Improved
Replace softmax with sigsoftmax3-layer LSTM · WT2 test + dynamic eval.perplexity: 43.3±0.1 -> 42.9 ± 0.1Improved
Replace MoS with MoSS3-layer LSTM mixture model · PTB test + dynamic eval.perplexity: 48.0±0.1 -> 47.7±0.07Improved
Replace MoS with MoSS3-layer LSTM mixture model · WT2 test + dynamic eval.perplexity: 40.8±0.03 -> 40.3±0.2Improved
Use sigmoid-based output instead of softmax (ablation)3-layer LSTM · PTB test + dynamic eval.perplexity: 50.5±0.5 -> 48.9 ± 0.3Improved
Use sigmoid-based output instead of softmax (ablation)3-layer LSTM · WT2 test + dynamic eval.perplexity: 43.3±0.1 -> 43.5±0.1Hurt
Use ReLU-based output instead of softmax (ablation)3-layer LSTM · PTB test + dynamic eval.perplexity: 50.5±0.5 -> (2.78±8)$\times 10^5$Hurt
Use ReLU-based output instead of softmax (ablation)3-layer LSTM · WT2 test + dynamic eval.perplexity: 43.3±0.1 -> (2.30±2)$\times 10^{4}$Hurt

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