ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspective.

Traditional deep learning interpretability methods which are suitable for model users cannot explain network behaviors at the global level and are inflexible at providing fine-grained explanations. As a solution, concept-based explanations are gaining attention due to their human intuitiveness and their flexibility to describe both global and local model behaviors. Concepts are groups of similarly meaningful pixels that express a notion, embedded within the network's latent space and have commonly been hand-generated, but have recently been discovered by automated approaches.

Use of Random T-DNA Mutagenesis in Identification of Gene , A Regulator of Conidiation, Stress Response, and Virulence in .

False smut of rice, caused by (Cooke) Takahashi (teleomorph: ), is one of the most important diseases affecting rice worldwide. -mediated transformation was used to identify functional genes in . In this study, we selected a single-copy insertion mutant T133 with deficiency in producing conidia by screening the T-DNA insertion mutant library of .