Amazing technological breakthrough possible @S-Logix pro@slogix.in

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • pro@slogix.in
  • +91- 81240 01111

Social List

Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation - 2020

Research Area:  Machine Learning

Abstract:

Most recent research of deep neural networks in the field of computer vision has focused on improving performances of point predictions by developing network architectures or learning algorithms. Reliable uncertainty quantification accompanied by point estimation can lead to a more informed decision, and the quality of prediction can be improved. In this paper, we invoke a Bayesian neural network and propose a natural way of quantifying uncertainties in classification problems by decomposing the moment-based predictive uncertainty into two parts: aleatoric and epistemic uncertainty. The proposed method takes into account the discrete nature of the outcome, yielding the correct interpretation of each uncertainty. We demonstrate that the proposed uncertainty quantification method provides additional insights into the point prediction using two Ischemic Stroke Lesion Segmentation Challenge datasets and the Digital Retinal Images for Vessel Extraction dataset.

Author(s) Name:  Yongchan Kwon,Joong-Ho Won,Beom Joon Kim,Myunghee Cho Paik

Journal name:  Computational Statistics & Data Analysis

Conferrence name:  

Publisher name:  ELSEVIER

DOI:  10.1016/j.csda.2019.106816

Volume Information:  Volume 142, February 2020, 106816