SOTAVerified

Dynamic neural networks

Dynamic neural networks are adaptable models that can change their structure or parameters during training or inference based on input complexity or computational constraints. They offer benefits like improved efficiency, adaptability, and scalability compared to static architectures.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 37 papers

TitleStatusHype
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference—0
Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNNCode0
Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural NetworksCode0
Long-Distance Gesture Recognition using Dynamic Neural Networks—0
Monadic Deep Learning—0
DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization—0
Stock Price Prediction using Dynamic Neural Networks—0
Evolving Artificial Neural Networks To Imitate Human Behaviour In Shinobi III : Return of the Ninja Master—0
GradMDM: Adversarial Attack on Dynamic Networks—0
Fixing Overconfidence in Dynamic Neural NetworksCode0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.