Search Results for author:
Found 6 papers, 1 papers with code
Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
Our findings prove that the expressiveness of the distribution can significantly influence the overall complexity of interpretation, and identify essential prerequisites that a model must possess to generate socially aligned explanations.
Local vs. Global Interpretability: A Computational Complexity Perspective
We propose a framework for bridging this gap, by using computational complexity theory to assess local and global perspectives of interpreting ML models.
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
This paper serves as a comprehensive system description of version 2. 0 of the Marabou framework for formal analysis of neural networks.
Formally Explaining Neural Networks within Reactive Systems
We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art.
Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networks
We (1) suggest an efficient, verification-based method for finding minimal explanations, which constitute a provable approximation of the global, minimum explanation; (2) show how DNN verification can assist in calculating lower and upper bounds on the optimal explanation; (3) propose heuristics that significantly improve the scalability of the verification process; and (4) suggest the use of bundles, which allows us to arrive at more succinct and interpretable explanations.
Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors
We proposed an unsupervised method for segmenting symbolic music.
