COMPUTER-IMPLEMENTED METHOD FOR PROVIDING INSIGHTS INTO MACHINE LEARNING MODELS

DE602023019851T2Active Publication Date: 2026-07-15ZENSEACT AB
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
ZENSEACT AB
Filing Date
2023-10-20
Publication Date
2026-07-15

AI Technical Summary

Technical Problem

The black box nature of machine learning models in autonomous vehicles makes it difficult to identify the cause of errors or inaccuracies in perception systems, hindering the improvement and development of automated driving systems.

Method used

Utilizing generative models to reconstruct input data and generate synthetic sensor data for comparison with original data, enabling visualization of the model's internal representation to identify potential errors or omissions.

Benefits of technology

This approach provides insight into the inner workings of machine learning models, facilitating error identification, improving system safety, and enabling targeted data collection for model enhancement.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader
Need to check novelty before this filing date? Find Prior Art
No text content released.