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 21–30 of 37 papers

TitleStatusHype
GradMDM: Adversarial Attack on Dynamic Networks—0
A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information—0
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference—0
An Introduction to Cognidynamics—0
Long-Distance Gesture Recognition using Dynamic Neural Networks—0
Monadic Deep Learning—0
Neuroevolving Electronic Dynamical Networks—0
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference—0
Analysis of Memory Organization for Dynamic Neural Networks—0
On-Demand Resource Management for 6G Wireless Networks Using Knowledge-Assisted Dynamic Neural Networks—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.