Interpretable AI from start to finish

Purpose and goal

** Denna text är maskinöversatt ** The technology with interpretable AI shall be used to provide transparency in development processes for AI-based products and services in order to understand, verify and validate the functionality of these, which is highly essential for AI development and use in Sweden. Methods and tools shall be developed to support a process from identifying the needs of users with AI and data to the delivery and reuse of products containing AI components. The technology shall also be compared with AI that is based on so-called black box models.

Expected effects and result

** Denna text är maskinöversatt ** The project intends to produce knowledge about how functionality in products can be created with AI in a way that can be interpreted and validated by those involved in the product development process. The results will facilitate the chang of application area of AI-based products when re-used or re-manufactured. The developed technology shell enable interpretable optimization of AI-based properties of products that have a direct connection to sustainability-affecting properties described in Agenda 2030.

Planned approach and implementation

** Denna text är maskinöversatt ** The project is organized around two practice cases. Use of route data of marine vesels to offer better propulsion systems and processing of data from airborne laser scanning of forests to discern interesting details in the stock. Methods and tools shall be developed to support a process from identifying the needs of users with AI and data to the delivery and reuse of products containing AI components. Research partners are RISE, Chalmers´ departments for mechanics and maritime sciences and Chalmers´ division for industry and materials science.