نسخة أولية وصول مفتوح
DASH: Fast, Valid Counterfactuals for Deep Networks via Batched Directional Search
Counterfactual explanations are most useful when they can be generated with low latency, remain close to the factual input, and satisfy input-domain, categorical, and actionability constraints. Achieving these objectives simultaneously is challenging for deep neural networks. Heuristic methods are often fast but may re …