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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “CNN-GP”

Calibrating Deep Convolutional Gaussian Processesstat.ML

New method calibrates CNN-GP models for better uncertainty quantification.

problem Current CNN-GP models are miscalibrated, leading to unreliable uncertainty estimates.

method Proposes a novel combination of CNNs and GPs to improve calibration.

result Significantly outperforms previous approaches on calibration while maintaining state-of-the-art performance.

Calibration Deep Convolutional Gaussian Processes Uncertainty Quantification CNN-GP Miscalibration

2018-05-26abs ↗pdf ↗

Enhanced Convolutional Neural Tangent Kernelscs.LG

Enhanced CNN kernels improve image classification accuracy.

problem Improving classification accuracy of CNNs.

method Local Average Pooling and random image patch representation.

result 89% accuracy on CIFAR-10, matching AlexNet performance.

CNN Kernel Image Classification Local Average Pooling Random Patches

2019-11-03abs ↗pdf ↗

Inferring transportation modes from GPS trajectories using a convolutional neural networkcs.LG

CNN predicts travel modes from GPS trajectories with 84.8% accuracy.

problem Inferring transportation modes from GPS data.

method CNN architecture for automatic feature extraction from raw GPS data.

result Highest accuracy of 84.8% achieved through ensemble of CNN configurations.

CNN GPS trajectories mode inference travel modes machine learning

2018-04-05abs ↗pdf ↗