paper-with-me

홈 › Papers

Explaining a prediction in some nonlinear models

2019-04-21 · Cosimo Izzo

In this article we will analyse how to compute the contribution of each input value to its aggregate output in some nonlinear models. Regression and classification applications, together with related algorithms for deep neural networks are presented. The proposed approach merges two methods currently present in the literature: integrated gradient and deep Taylor decomposition. Compared to DeepLIFT and Deep SHAP, it provides a natural choice of the reference point peculiar to the model at use.

📄 PDF Abstract BibTeX arXiv:1904.09615

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationPredictionregression

Methods 이 논문이 사용한 방법론

SHAP 설명 없음

Similar Papers 제목 키워드 기반

Predicting and explaining nonlinear material response using deep Physically Guided Neural Networks with Internal Variables

2023-08-07 · Javier Orera-Echeverria, Jacobo Ayensa-Jiménez, Manuel Doblare

Nonlinear materials are often difficult to model with classical state model theory because they have a complex and sometimes inaccurate physical and mathematical description or we simply do not know how to describe such …

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

An Interpretable Probabilistic Model for Short-Term Solar Power Forecasting Using Natural Gradient Boosting

2021-08-05 · Georgios Mitrentsis, Hendrik Lens

PV power forecasting models are predominantly based on machine learning algorithms which do not provide any insight into or explanation about their predictions (black boxes). Therefore, their direct implementation in env…

Prediction Intervals

Stability Properties of Graph Neural Networks

2019-05-11 · Fernando Gama, Joan Bruna, Alejandro Ribeiro

Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others. GNNs consists…

Motion PlanningRecommendation Systems

Explaining Bayesian Neural Networks

2021-08-23 · Kirill Bykov, Marina M. -C. Höhne, Adelaida Creosteanu, Klaus-Robert Müller 외

To make advanced learning machines such as Deep Neural Networks (DNNs) more transparent in decision making, explainable AI (XAI) aims to provide interpretations of DNNs' predictions. These interpretations are usually giv…

Decision MakingExplainable Artificial Intelligence (XAI)

Explaining the Predictions of Any Image Classifier via Decision Trees

2019-11-04 · Sheng Shi, Xinfeng Zhang, Wei Fan

Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and predic…

Prediction