UCI HAR
PulseAugur coverage of UCI HAR — every cluster mentioning UCI HAR across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
ChroNoC: Tableless NoC Enhances Neuromorphic Computing Efficiency
Researchers have developed ChroNoC, a novel tableless Time-Division Multiplexing (TDM) network-on-chip (NoC) designed for time-sensitive neuromorphic computing. This system embeds broadcast trees into combinational logi…
-
LightSplit enhances privacy in split learning with orthogonal projections
Researchers have developed LightSplit, a novel approach to privacy-preserving split learning that uses orthogonal projections to reduce communication overhead and protect against reconstruction attacks. This method part…
-
New research questions trust in machine learning matching principles
A new research paper explores the reliability of the matching principle in machine learning, particularly in scenarios with finite-sample and model uncertainty. The study quantifies decision-making trust through a ratio…
-
New MCIR-M method improves ML model explainability with feature dependence awareness
Researchers have introduced MCIR-M, a new method for explaining machine learning models that accounts for feature dependence. Traditional methods like SHAP and LIME can struggle with correlated or redundant features, le…
-
TreeCCA integrates gradient-boosted trees for interpretable correlation analysis
Researchers have developed TreeCCA, a novel method that integrates gradient-boosted trees into canonical correlation analysis (CCA). This approach allows for end-to-end training of tree ensembles as CCA encoders, offeri…
-
New method calibrates temporal classification by separating representation and decision errors
This paper introduces a novel approach to temporal classification by decomposing errors into representation failures and decision-making issues. The proposed method involves freezing a trained classifier and adding two …