A Human-In-the-Loop System for Interpreting Image Recognition Models

A Human-In-the-Loop System for Interpreting Image Recognition Models

Ziengs, Bart (TU Delft Electrical Engineering, Mathematics and Computer Science)

Yang, J. (mentor)
Houben, G.J.P.M. (mentor)
Cruz, Luis (graduation committee)
Yorke-Smith, N. (graduation committee)

Delft University of Technology

Computer Science

2022-06-01

Interpretability of ML models and image recognition models specifaclly, is a increasing problem. In this thesis, the design and implementation of Brickroutine: a system that used a trained model, is presented. Using human annotations, semantic interpretations are given to image classification problems. By giving an iterative approach in terms of workflows and technically designing it in a modular, salable way using Docker, the authors aim for bridging the gap between performance and interpretability of AI by combining human and computational intelligence.

machine learning
interpretability
Human-in-the-loop

http://resolver.tudelft.nl/uuid:6ebbdf05-e37d-45b9-b0ad-1844c9d7f298

Student theses

master thesis

© 2022 Bart Ziengs