3.2.1 Managing failures of machine learned elements

Assurance objective: Implement effective mitigations for identified sources of deviation for elements of the system implemented using ML.

Contextual description: Any identified mechanism that could cause an ML implementation to deviate from its implementation during operation must be shown to be effectively managed. This may necessitate the definition of additional requirements for implementation, or changes to the system design.

Practical guidance: To be determined.

Contact us

Assuring Autonomy International Programme

assuring-autonomy@york.ac.uk
+44 (0)1904 325345
Institute for Safe Autonomy, University of York, Deramore Lane, York YO10 5GH

Contact us

Assuring Autonomy International Programme

assuring-autonomy@york.ac.uk
+44 (0)1904 325345
Institute for Safe Autonomy, University of York, Deramore Lane, York YO10 5GH