Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952511863> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W2952511863 abstract "Symmetric networks designed for energy minimization such as Boltzman machines and Hopfield nets are frequently investigated for use in optimization, constraint satisfaction and approximation of NP-hard problems. Nevertheless, finding a global solution (i.e., a global minimum for the energy function) is not guaranteed and even a local solution may take an exponential number of steps. We propose an improvement to the standard local activation function used for such networks. The improved algorithm guarantees that a global minimum is found in linear time for tree-like subnetworks. The algorithm, called activate, is uniform and does not assume that the network is tree-like. It can identify tree-like subnetworks even in cyclic topologies (arbitrary networks) and avoid local minima along these trees. For acyclic networks, the algorithm is guaranteed to converge to a global minimum from any initial state of the system (self-stabilization) and remains correct under various types of schedulers. On the negative side, we show that in the presence of cycles, no uniform algorithm exists that guarantees optimality even under a sequential asynchronous scheduler. An asynchronous scheduler can activate only one unit at a time while a synchronous scheduler can activate any number of units in a single time step. In addition, no uniform algorithm exists to optimize even acyclic networks when the scheduler is synchronous. Finally, we show how the algorithm can be improved using the cycle-cutset scheme. The general algorithm, called activate-with-cutset, improves over activate and has some performance guarantees that are related to the size of the network's cycle-cutset." @default.
- W2952511863 created "2019-06-27" @default.
- W2952511863 creator A5053651798 @default.
- W2952511863 creator A5086804592 @default.
- W2952511863 date "1995-09-30" @default.
- W2952511863 modified "2023-10-05" @default.
- W2952511863 title "Improving Connectionist Energy Minimization" @default.
- W2952511863 doi "https://doi.org/10.48550/arxiv.cs/9510102" @default.
- W2952511863 hasPublicationYear "1995" @default.
- W2952511863 type Work @default.
- W2952511863 sameAs 2952511863 @default.
- W2952511863 citedByCount "0" @default.
- W2952511863 crossrefType "posted-content" @default.
- W2952511863 hasAuthorship W2952511863A5053651798 @default.
- W2952511863 hasAuthorship W2952511863A5086804592 @default.
- W2952511863 hasBestOaLocation W29525118631 @default.
- W2952511863 hasConcept C111919701 @default.
- W2952511863 hasConcept C113174947 @default.
- W2952511863 hasConcept C11413529 @default.
- W2952511863 hasConcept C126255220 @default.
- W2952511863 hasConcept C134306372 @default.
- W2952511863 hasConcept C14036430 @default.
- W2952511863 hasConcept C147764199 @default.
- W2952511863 hasConcept C151319957 @default.
- W2952511863 hasConcept C186633575 @default.
- W2952511863 hasConcept C199845137 @default.
- W2952511863 hasConcept C31258907 @default.
- W2952511863 hasConcept C33923547 @default.
- W2952511863 hasConcept C41008148 @default.
- W2952511863 hasConcept C78458016 @default.
- W2952511863 hasConcept C86803240 @default.
- W2952511863 hasConceptScore W2952511863C111919701 @default.
- W2952511863 hasConceptScore W2952511863C113174947 @default.
- W2952511863 hasConceptScore W2952511863C11413529 @default.
- W2952511863 hasConceptScore W2952511863C126255220 @default.
- W2952511863 hasConceptScore W2952511863C134306372 @default.
- W2952511863 hasConceptScore W2952511863C14036430 @default.
- W2952511863 hasConceptScore W2952511863C147764199 @default.
- W2952511863 hasConceptScore W2952511863C151319957 @default.
- W2952511863 hasConceptScore W2952511863C186633575 @default.
- W2952511863 hasConceptScore W2952511863C199845137 @default.
- W2952511863 hasConceptScore W2952511863C31258907 @default.
- W2952511863 hasConceptScore W2952511863C33923547 @default.
- W2952511863 hasConceptScore W2952511863C41008148 @default.
- W2952511863 hasConceptScore W2952511863C78458016 @default.
- W2952511863 hasConceptScore W2952511863C86803240 @default.
- W2952511863 hasLocation W29525118631 @default.
- W2952511863 hasLocation W29525118632 @default.
- W2952511863 hasOpenAccess W2952511863 @default.
- W2952511863 hasPrimaryLocation W29525118631 @default.
- W2952511863 hasRelatedWork W2001455358 @default.
- W2952511863 hasRelatedWork W2040032566 @default.
- W2952511863 hasRelatedWork W2108861020 @default.
- W2952511863 hasRelatedWork W2121922170 @default.
- W2952511863 hasRelatedWork W2367372208 @default.
- W2952511863 hasRelatedWork W2378960857 @default.
- W2952511863 hasRelatedWork W4210838092 @default.
- W2952511863 hasRelatedWork W4250124476 @default.
- W2952511863 hasRelatedWork W639208967 @default.
- W2952511863 hasRelatedWork W2105069372 @default.
- W2952511863 isParatext "false" @default.
- W2952511863 isRetracted "false" @default.
- W2952511863 magId "2952511863" @default.
- W2952511863 workType "article" @default.