<ul><li>Recent advancements have shown the possibility of obtaining explanations with formal guarantees for neural networks using verification techniques.</li><li>A novel abstraction-refinement technique has been proposed to efficiently compute provably sufficient explanations of neural network predictions.</li><li>The method involves abstracting the original neural network into a reduced network to speed up the verification process.</li><li>Experiments show that this approach improves the efficiency of obtaining provably sufficient explanations for neural network predictions.</li></ul>

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

Discover more