arXiv:2007.00758
In-Distribution Interpretability for Challenging Modalities
원문 초록
It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches. However, the development of methods to investigate the mode of operation of such models has advanced rapidly in the past few years. Recent work introduced an intuitive framework which utilizes generative models to improve on the meaningfulness of such explanations. In this work, we display the flexibility of this method to interpret diverse and challenging modalities: music 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.