On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “threshold-moving”

Reviving Threshold-Moving: a Simple Plug-in Bagging Ensemble for Binary and Multiclass Imbalanced Datacs.LG

A new method combines bagging and threshold-moving for imbalanced data.

problem Class imbalance in data mining hinders model performance.

method Probability thresholding bagging (PT-bagging) that preserves natural class distribution.

result PT-bagging improves model performance on imbalanced data.

imbalanced data threshold-moving probability thresholding bagging ensemble binary and multiclass

2016-06-28abs ↗pdf ↗

Revisiting Distillation and Incremental Classifier Learningcs.LG

Paper aims to improve AI's ability to learn new tasks incrementally.

problem Catastrophic Forgetting in AI systems learning multiple tasks simultaneously.

method Analyzed iCaRL method, identified knowledge distillation as key, proposed dynamic threshold moving algorithm.

result Demonstrated effectiveness of dynamic threshold moving algorithm on CIFAR100 and MNIST datasets.

Catastrophic Forgetting Incremental Learning Knowledge Distillation Dynamic Threshold Moving CIFAR100

2018-07-08abs ↗pdf ↗

Deep ensemble learning for Alzheimers disease classificationcs.LG

Deep learning ensemble improves Alzheimer's disease classification accuracy.

problem Improving diagnostic accuracy for Alzheimer's disease.

method Proposes a deep ensemble learning framework integrating multisource data and expert wisdom.

result 4% improvement in classification accuracy compared to existing methods.

Alzheimer's disease Deep learning Ensemble methods Clinical data Feature learning

2019-05-30abs ↗pdf ↗