A shared mixed-activation network of width 2dN+d+2 yields layer-wise L^p approximation rates bounded by the modulus of continuity at geometric scale N^{-ℓ}, reducing to (2d+1)N^{-ℓ} for 1-Lipschitz targets.
On a sparse shortcut topology of artificial neural networks.IEEE Transactions on Artificial Intelligence, 3(4):595–608
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Jointλ provides a distributed, function-side orchestration layer with Backend-Shim compatibility and datastore-based failover that runs serverless workflows on heterogeneous Jointcloud FaaS systems, delivering up to 3.3× lower makespan and 65% cost reduction versus single-cloud commercial services.
A systematic mapping study of 87 papers derives an architecture-based taxonomy for Workflow as a Service brokers and identifies future research directions.
citing papers explorer
-
Geometric Layer-wise Approximation Rates for Deep Networks
A shared mixed-activation network of width 2dN+d+2 yields layer-wise L^p approximation rates bounded by the modulus of continuity at geometric scale N^{-ℓ}, reducing to (2d+1)N^{-ℓ} for 1-Lipschitz targets.
-
Joint$\lambda$: Orchestrating Serverless Workflows on Jointcloud FaaS Systems
Jointλ provides a distributed, function-side orchestration layer with Backend-Shim compatibility and datastore-based failover that runs serverless workflows on heterogeneous Jointcloud FaaS systems, delivering up to 3.3× lower makespan and 65% cost reduction versus single-cloud commercial services.
-
Workflow as a Service Broker in Cloud Environment: A Systematic Mapping Study
A systematic mapping study of 87 papers derives an architecture-based taxonomy for Workflow as a Service brokers and identifies future research directions.