Traceability of Deep Neural Networks
This addresses the problem of ensuring safety and compliance in critical applications using deep learning, though it is incremental as it adapts existing traceability concepts rather than introducing a new paradigm.
The paper tackles the challenge of applying traditional software traceability standards to deep neural networks, which lack clear code and low-level requirements, by proposing new artifacts and traceability forms to accommodate the trial-and-error development process.
[Context.] The success of deep learning makes its usage more and more tempting in safety-critical applications. However such applications have historical standards (e.g., DO178, ISO26262) which typically do not envision the usage of machine learning. We focus in particular on \emph{requirements traceability} of software artifacts, i.e., code modules, functions, or statements (depending on the desired granularity). [Problem.] Both code and requirements are a problem when dealing with deep neural networks: code constituting the network is not comparable to classical code; furthermore, requirements for applications where neural networks are required are typically very hard to specify: even though high-level requirements can be defined, it is very hard to make such requirements concrete enough, that one can qualify them of low-level requirements. An additional problem is that deep learning is in practice very much based on trial-and-error, which makes the final result hard to explain without the previous iterations. [Proposed solution.] We investigate which artifacts could play a similar role to code or low-level requirements in neural network development and propose various traces which one could possibly consider as a replacement for classical notions. We also propose a form of traceability (and new artifacts) in order to deal with the particular trial-and-error development process for deep learning.