paper-with-me

홈 › Papers

Layer-Stack Temperature Scaling

2022-11-18 · Amr Khalifa, Michael C. Mozer, Hanie Sedghi, Behnam Neyshabur, Ibrahim Alabdulmohsin

Recent works demonstrate that early layers in a neural network contain useful information for prediction. Inspired by this, we show that extending temperature scaling across all layers improves both calibration and accuracy. We call this procedure "layer-stack temperature scaling" (LATES). Informally, LATES grants each layer a weighted vote during inference. We evaluate it on five popular convolutional neural network architectures both in- and out-of-distribution and observe a consistent improvement over temperature scaling in terms of accuracy, calibration, and AUC. All conclusions are supported by comprehensive statistical analyses. Since LATES neither retrains the architecture nor introduces many more parameters, its advantages can be reaped without requiring additional data beyond what is used in temperature scaling. Finally, we show that combining LATES with Monte Carlo Dropout matches state-of-the-art results on CIFAR10/100.

📄 PDF Abstract BibTeX arXiv:2211.10193

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Monte Carlo Dropout 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Short sighted deep learning

2020-02-07 · Ellen de Melllo Koch, Anita de Mello Koch, Nicholas Kastanos, Ling Cheng

A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization group (RG). This idea has been explored i…

Deep Learning

Improving the Post-hoc Calibration of Modern Neural Networks with Probe Scaling

2021-09-29 · Amr Khalifa, Ibrahim Alabdulmohsin

We present "probe scaling": a post-hoc recipe for calibrating the predictions of modern neural networks. Our recipe is inspired by several lines of work, which demonstrate that early layers in the neural network learn ge…

Spatio-temporal Stacked LSTM for Temperature Prediction in Weather Forecasting

2018-11-15 · Zahra Karevan, Johan A. K. Suykens

Long Short-Term Memory (LSTM) is a well-known method used widely on sequence learning and time series prediction. In this paper we deployed stacked LSTM model in an application of weather forecasting. We propose a 2-laye…

PredictionTime SeriesTime Series AnalysisTime Series Prediction+1

Hierarchical LoRA MoE for Efficient CTR Model Scaling

2025-10-12 · Zhichen Zeng, Mengyue Hang, Xiaolong Liu, Xiaoyi Liu 외 arxiv

Deep models have driven significant advances in click-through rate (CTR) prediction. While vertical scaling via layer stacking improves model expressiveness, the layer-by-layer sequential computation poses challenges to …

Design of the PID temperature controller for an alkaline electrolysis system with time delays

2022-10-03 · Ruomei Qi, Jiarong Li, Jin Lin, Yonghua Song 외

Electrolysis systems use proportional-integral-derivative (PID) temperature controllers to maintain stack temperatures around set points. However, heat transfer delays in electrolysis systems cause manual tuning of PID t…