Towards Formal Approximated Minimal Explanations of Neural Networks
- Shahaf Bassan, Guy Katz
- Computer ScienceArXiv
- 2022
This work considers this work as a step toward leveraging verification technology in producing DNNs that are more reliable and comprehensible, and recommends the use of bundles, which allows us to arrive at more succinct and interpretable explanations.
Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors
- Shahaf Bassan, Yossi Adi, J. Rosenschein
- Computer ScienceInterspeech
- 2 July 2022
The proposed unsupervised method for segment-ing symbolic music is based on an ensemble of temporal prediction error models, which is inferior to the supervised setting, which leaves room for improvement in future research considering closing the gap between unsuper supervised and supervised methods.
Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networks
- Shahaf Bassan, Guy Katz
- Computer Science
- 25 October 2022
This work suggests an efficient, verification-based method for finding minimal explanations, which constitute a provable approximation of the global, minimum explanation, and proposes heuristics that significantly improve the scalability of the verification process.