Saved in:
Bibliographic Details
Main Authors: Agrawal, Chandan, Papanai, Ashish, White, Jerome
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2402.00015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910409253978112
author Agrawal, Chandan
Papanai, Ashish
White, Jerome
author_facet Agrawal, Chandan
Papanai, Ashish
White, Jerome
contents This paper describes and evaluates a multistage approach to AI deployment. Each stage involves a more accurate method of inference, yet engaging each comes with an increasing cost. In outlining the architecture, we present a method for quantifying model uncertainty that facilitates confident deferral decisions. The architecture is currently under active deployment to thousands of cotton farmers across India. The broader idea however is applicable to a growing sector of AI deployments in challenging low resources settings.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00015
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Maintaining User Trust Through Multistage Uncertainty Aware Inference
Agrawal, Chandan
Papanai, Ashish
White, Jerome
Artificial Intelligence
Computer Vision and Pattern Recognition
This paper describes and evaluates a multistage approach to AI deployment. Each stage involves a more accurate method of inference, yet engaging each comes with an increasing cost. In outlining the architecture, we present a method for quantifying model uncertainty that facilitates confident deferral decisions. The architecture is currently under active deployment to thousands of cotton farmers across India. The broader idea however is applicable to a growing sector of AI deployments in challenging low resources settings.
title Maintaining User Trust Through Multistage Uncertainty Aware Inference
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.00015