Methods › General › Activation Functions › ASU

Amplifying Sine Unit: An Oscillatory Activation Function for Deep Neural Networks to Recover Nonlinear Oscillations Efficiently

ASU

9 papers tagged archive 2025-07-28

Introduced by Dmytro Mishkin et al. in ArXiving Before Submission Helps Everyone

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

2023

Papers archive 2025-07-28

9 shown of 9, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Hierarchical RL-MPC for Demand Response Scheduling
19 Feb 2025 · 0 repositories · arXiv:2502.13714
TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality
27 Apr 2024 · 0 repositories · arXiv:2404.17983
ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
8 Mar 2024 · 0 repositories · arXiv:2403.05326
Profit and loss attribution: An empirical study
14 Sep 2023 · 0 repositories · arXiv:2309.07667
Data-Driven Model Reduction and Nonlinear Model Predictive Control of an Air Separation Unit by Applied Koopman Theory
11 Sep 2023 · 0 repositories · arXiv:2309.05386
ASU-CNN: An Efficient Deep Architecture for Image Classification and Feature Visualizations
28 May 2023 · 0 repositories · arXiv:2305.19146
Amplifying Sine Unit: An Oscillatory Activation Function for Deep Neural Networks to Recover Nonlinear Oscillations Efficiently
18 Apr 2023 · 0 repositories · arXiv:2304.09759
Action State Update Approach to Dialogue Management
9 Nov 2020 · 0 repositories · arXiv:2011.04637
ArXiving Before Submission Helps Everyone
11 Oct 2020 · 0 repositories · arXiv:2010.05365

Tasks archive 2025-07-28

16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

Task	Papers
Model Predictive Control	2
Active Learning	1
CPU	1
Dialogue Management	1
Hallucination	1
Image Classification	1
Imputation	1
Management	1
Natural Language Understanding	1
Question Answering	1
Reinforcement Learning (RL)	1
Scheduling	1
Text to Speech	1
image-classification	1
model	1
text-to-speech	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (9 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Activation Functions

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections