Data Uncertainty without Prediction Models

2022-04-25 · Bongjoon Park, Eunkyung Koh

Data acquisition processes for machine learning are often costly. To construct a high-performance prediction model with fewer data, a degree of difficulty in prediction is often deployed as the acquisition function in adding a new data point. The degree of difficulty is referred to as uncertainty in prediction models. We propose an uncertainty estimation method named a Distance-weighted Class Impurity without explicit use of prediction models. We estimated uncertainty using distances and class impurities around the location, and compared it with several methods based on prediction models for uncertainty estimation by active learning tasks. We verified that the Distance-weighted Class Impurity works effectively regardless of prediction models.

📄 PDF Abstract BibTeX arXiv:2204.11858

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning Prediction

Exploring Uncertainty in Deep Learning for Construction of Prediction Intervals

2021-04-27 · Yuandu Lai, Yucheng Shi, Yahong Han, Yunfeng Shao 외

Deep learning has achieved impressive performance on many tasks in recent years. However, it has been found that it is still not enough for deep neural networks to provide only point estimates. For high-risk tasks, we ne…

Deep Learning Prediction Prediction Intervals

Efficient Normalized Conformal Prediction and Uncertainty Quantification for Anti-Cancer Drug Sensitivity Prediction with Deep Regression Forests

2024-02-21 · Daniel Nolte, Souparno Ghosh, Ranadip Pal

Deep learning models are being adopted and applied on various critical decision-making tasks, yet they are trained to provide point predictions without providing degrees of confidence. The trustworthiness of deep learnin…

Conformal Prediction Decision Making Deep Learning Drug Response Prediction+5

Uncertainty-aware Human Motion Prediction

2021-07-08 · Pengxiang Ding, Jianqin Yin

Human motion prediction is essential for tasks such as human motion analysis and human-robot interactions. Most existing approaches have been proposed to realize motion prediction. However, they ignore an important task,…

Human motion prediction motion prediction Prediction

Deep Deterministic Uncertainty: A Simple Baseline

2021-02-23 · Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr 외

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncerta…

Active Learning Uncertainty Quantification

Probabilistic Concept Bottleneck Models

2023-06-02 · Eunji Kim, Dahuin Jung, Sangha Park, Siwon Kim 외

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the pre…

Prediction