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 26–37 of 37 papers

TitleStatusHype
DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNINGCode0
Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network—0
Siamese Labels Auxiliary Learning—0
Dynamic Neural Networks: A Survey—0
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck ApproachCode1
Dynamic Dual Gating Neural NetworksCode1
Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference—0
Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison—0
Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks—0
AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural NetworksCode0
Nonlinear Systems Identification Using Deep Dynamic Neural NetworksCode0
Analysis of Memory Organization for Dynamic Neural Networks—0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.