KIT data specialists develop strategies on how methods and procedures of explainable AI can be applied to your use case. Taking into account global and local explainability, state-of-the-art tools are presented and further recommendations for action are given so that you can develop better representations for decision makers and make processes more transparent.
Many applications require human oversight of automated decision making. This may result from direct application requirements (e.g. computer assisted maintenance tasks) or legal obligations, such as those contained in the GDPR as part of Article 22.
In contrast, many modern machine learning algorithms represent complex black boxes that can hardly be understood by humans. However, the explainability of models using ML algorithms can be achieved in different ways at different levels.
Identifying the appropriate strategy can depend heavily on the application and needs to be evaluated. We offer technical implementations ranging from compositional feature generation to locally interpretable model-agnostic explanations.
While explainability based on concrete model decisions is easy to achieve for image data, our expertise lies in providing explanatory approaches for high-dimensional data such as multivariate time series. We can provide services that can be integrated as visualizations in dashboards or reports to meet your business needs.
SPECIAL ACCESS CONDITIONS
Conditions and requirements for participation in an experiment within the Open Calls:
By participating in an EUHubs4Data Open Call, you are initially only applying for funding that originally comes from the European Commission and is awarded by the coordinator exclusively in its own name under the conclusion of a sub-grant agreement. This sub-grant agreement does not establish a contract with KIT, neither through your application nor through a possible positive funding decision.
KIT will therefore - also in your own interest - conclude a separate written agreement with you at the start of the experiment (based on our sample cooperation agreement. If you decide to propose the participation of KIT and SDIL infrastructure in your experiment, you must respect the following conditions. We provide this information in advance to ensure maximum transparency: please contact us if you have any questions. In the unlikely event that you are unable to conduct your experiment with our participation, we will attempt to assist you in selecting alternative services before the experiment begins.
Please note that contrary to the name "service", the above description is not a genuine commercial offer, but a listing of exclusive contributions as part of a genuine eye-to-eye collaboration.
For genuine commercial offerings related to the above topics, please feel free to contact us any time outside of the Open Calls.
Clear specification of the machine learning objective, fitting labeled data set(s).
We have successfully employed model explaination strategies in multiple of our consulting projects giving insights for process improvement.
This is an example from the chemical industry: https://www.sdil.de/en/projects/fuchs-2
SERVICE CAN BE COMBINED WITH
Explainable model development can be used as addon to any ML model delevopment services as long as model learning can be replicated on KIT's infrastructure, which is included as part of the service (you explicitly select it together with the service).