arXiv:2110.08252
A Rate-Distortion Framework for Explaining Black-box Model Decisions
원문 초록
We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations of the target input signal and applies to any differentiable pre-trained model such as neural networks. Our experiments demonstrate the framework's adaptability to diverse data modalities, particularly images, audio, and physical simulations of urban environments.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
Adversarial Manhole: Challenging Monocular Depth Estimation and Semantic Segmentation Models with Patch Attack
Efficient Probabilistic Modeling of Crystallization at Mesoscopic Scale
Interpolating neural network: A novel unification of machine learning and interpolation theory
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer
토론
이 논문과 연결된 포럼 글이 아직 없습니다.