• StarPU

  • Referenced in 41 articles [sw14216]
  • tuned per-task performance models, can be used to greatly improve the quality of scheduling...
  • SATzilla

  • Referenced in 100 articles [sw06281]
  • that use so-called empirical hardness models to choose among their constituent solvers. This approach ... score in a competition). The excellent performance of SATzilla was independently verified ... improving it by integrating local search solvers as candidate solvers, by predicting performance score instead ... runtime, and by using hierarchical hardness models that take into account different types...
  • BSPlib

  • Referenced in 42 articles [sw03374]
  • Portable and architecture independent parallel performance tuning using BSP. A call-graph profiling tool ... program code which are amenable to improvement. A unique feature of this profiler is that ... cost model, thus providing a mechanism for portable and architecture-independent parallel performance tuning...
  • MobileNetV2

  • Referenced in 17 articles [sw41926]
  • MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks ... different model sizes. We also describe efficient ways of applying these mobile models to object ... demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which ... representational power. We demonstrate that this improves performance and provide an intuition that...
  • Chameleon

  • Referenced in 8 articles [sw17690]
  • proposed application scheduling model. Chameleon shows performance improvements in data intensive applications that require both...
  • cmenet

  • Referenced in 8 articles [sw21048]
  • reduction to efficiently perform model selection. Simulation studies demonstrate the improved performance of cmenet over...
  • Rabbit

  • Referenced in 24 articles [sw01317]
  • model and an estimate of the BDD size. This leads to a significant performance improvement...
  • cuDNN

  • Referenced in 14 articles [sw17848]
  • convolutional networks, improves performance by 36% on a standard model while also reducing memory consumption...
  • Ninf-G/MPI

  • Referenced in 45 articles [sw03461]
  • master-worker type parallel programming models. In order to improve the parallel efficiency ... Ninf-G and MPI. We examined the performance of the proposed method in an environment...
  • SparseM

  • Referenced in 24 articles [sw10534]
  • illustrated by a family of linear model fitting functions that implement least squares methods ... problems with sparse design matrices. Significant performance improvements in memory utilization and computational speed...
  • ALBERT

  • Referenced in 9 articles [sw36207]
  • results in improved performance on downstream tasks. However, at some point further model increases become...
  • Vensim

  • Referenced in 15 articles [sw12336]
  • Vensim is simulation software for improving the performance of real systems. Vensim is used ... developing, analyzing, and packaging dynamic feedback models. We emphasize: High quality, with dimensional consistency...
  • BioProspector

  • Referenced in 29 articles [sw09375]
  • motif. In addition, BioProspector can model gapped motifs and motifs with palindromic patterns, which ... prokaryotes. All these modifications greatly improve the performance of the program. Besides showing preliminary success...
  • UPPAAL CORA

  • Referenced in 9 articles [sw25660]
  • about the model to the tool, which in turn can improve the performance of UPPAAL...
  • AIS-BN

  • Referenced in 25 articles [sw02223]
  • very large Bayesian network models, have been observed to perform poorly in evidential reasoning with ... algorithms consistently. Three sources of this performance improvement are (1) two heuristics for initialization ... algorithm. par We tested the performance of the AIS-BN algorithm along with two state ... tests three large real Bayesian network models available to the scientific community: the CPCS network...
  • ParEGO

  • Referenced in 68 articles [sw10968]
  • hypercube and updates a Gaussian processes surrogate model of the search landscape after every function ... estimate the solution of largest expected improvement. The two algorithms are tested using a benchmark ... this can be used to understand performance differences. Both algorithms perform well but ParEGO comes...
  • RLT-POS

  • Referenced in 3 articles [sw18321]
  • each model enhancement has been shown in previous papers to significantly improve the performance ... between different model enhancement techniques becomes critical for an improved overall performance since special structures ... might be lost after implementing some other model enhancement. More specifically, we discuss the coordination ... demonstrate the improvement over a standard RLT implementation and to compare the performances...
  • CBAM

  • Referenced in 8 articles [sw42531]
  • experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide...
  • PicHunter

  • Referenced in 53 articles [sw14896]
  • select images for display. Details of our model of a user’s behavior were tuned ... that the performance of current image database retrieval systems can be improved by incorporation...
  • RUSBoost

  • Referenced in 5 articles [sw20607]
  • RUSBoost: Improving classification performance when training data is skewed. Constructing classification models using skewed training ... improving classification performance when training data is imbalanced. In addition to performing favorably when compared ... than SMOTEBoost and results in significantly shorter model training times. This combination of simplicity, speed...