AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Neural Power Units

Niklas Heim, Tomas Pevny, Vasek Smidl

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability · 4 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 NPU rather than NALUtwo-layer arithmetic models · Simple arithmetic task (+, ×, ÷, √)testing error: NALU: 2.69 ± 0.22, 4.55 ± 0.2, 3.33 ± 0.18, 0.034 ± 0.006; NPU: 0.2 ± 0.11, 0.37 ± 0.23, 0.23 ± 0.13, 0.031 ± 0.025Improved
Remove imaginary parameters from NPU (ablation)NPU · Simple arithmetic task (+, ×, ÷, √)testing error: NPU: 0.2 ± 0.11, 0.37 ± 0.23, 0.23 ± 0.13, 0.031 ± 0.025; RealNPU: 0.08 ± 0.021, 0.066 ± 0.026, 0.085 ± 0.038, 0.004 ± 0Improved
Use NMU rather than NPUarithmetic models · Simple arithmetic task (×)testing error: 0.37 ± 0.23 -> 0.005 ± 0.004Improved
Use NPU rather than NMUarithmetic models · Simple arithmetic task (÷)testing error: 11.399 ± 0.035 -> 0.23 ± 0.13Improved
Use NPU rather than NMUarithmetic models · Simple arithmetic task (√)testing error: 0.16 ± 0.002 -> 0.031 ± 0.025Improved
Use NMU rather than NPUarithmetic models · Large scale arithmetic task (+)testing MSE: 0.092 ± 0.031 -> 0.00602 ± 0.00019Improved
Use NMU rather than NPUarithmetic models · Large scale arithmetic task (×)testing MSE: 4.28 ± 0.9 -> 1.7 ± 1.4Improved
Use NPU rather than NMUarithmetic models · Large scale arithmetic task (÷)testing MSE: 1.622 ± 0.081 -> 1.0e-7 ± 1.0e-7Improved
Use NPU rather than NMUarithmetic models · Large scale arithmetic task (√)testing MSE: 10.96 ± 0.89 -> 0.054 ± 0.0078Improved
Add the relevance gate (ablation)NaiveNPU · Large scale arithmetic task (+, ×, ÷, √)testing MSE: NaiveNPU: 161.65 ± 0.11, 3750.0 ± 870.0, 5.4e17 ± 5.4e17, 9.3e8 ± 9.3e8; NPU: 0.092 ± 0.031, 4.28 ± 0.9, 1.0e-7 ± 1.0e-7Improved
Remove imaginary parameters from NPU (ablation)NPU · Large scale arithmetic task (×)testing MSE: 4.28 ± 0.9 -> 3.09 ± 0.74Improved
Remove imaginary parameters from NPU (ablation)NPU · Large scale arithmetic task (÷)testing MSE: 1.0e-7 ± 1.0e-7 -> 1.4e-6 ± 4.0e-7Hurt

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