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 1–10 of 37 papers

TitleStatusHype
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor FusionCode1
Parametric Taylor series based latent dynamics identification neural networks—0
An Introduction to Cognidynamics—0
DyFADet: Dynamic Feature Aggregation for Temporal Action DetectionCode1
Neuroevolving Electronic Dynamical Networks—0
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded DevicesCode1
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
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.