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
DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNINGCode0
Fixing Overconfidence in Dynamic Neural NetworksCode0
Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNNCode0
Nonlinear Systems Identification Using Deep Dynamic Neural NetworksCode0
SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networksCode0
ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines—0
Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network—0
Evolving Artificial Neural Networks To Imitate Human Behaviour In Shinobi III : Return of the Ninja Master—0
Stock Price Prediction using Dynamic Neural Networks—0
Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison—0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.