A
Ajay Chander
Researcher at Fujitsu
Publications - 51
Citations - 439
Ajay Chander is an academic researcher from Fujitsu. The author has contributed to research in topics: Temporal resolution & Topic model. The author has an hindex of 7, co-authored 51 publications receiving 283 citations.
Papers
More filters
Book ChapterDOI
Explainable AI: The new 42?
Randy Goebel,Ajay Chander,Katharina Holzinger,Freddy Lecue,Zeynep Akata,Zeynep Akata,Simone Stumpf,Peter Kieseberg,Andreas Holzinger,Andreas Holzinger +9 more
TL;DR: Explainable AI is not a new field but the evolution of formal reasoning architectures to incorporate principled probabilistic reasoning helped address the capture and use of uncertain knowledge.
Working with Beliefs: AI Transparency in the Enterprise.
TL;DR: Working with enterprise decision makers considering AI in a decision augmentation role reveals an additional and possibly more crucial aspect of choosing an AI: the ability of decision makers to interact fluidly with an AI.
Proceedings ArticleDOI
Explanation Perspectives from the Cognitive Sciences---A Survey
Ramya Srinivasan,Ajay Chander +1 more
TL;DR: This work surveys papers from the cognitive science literature that address the following broad questions: what is an explanation, what are explanations for, and what are the characteristics of good and bad explanations, and organizes the insights gained by means of highlighting the advantages and shortcomings of various explanation structures and theories.
Journal ArticleDOI
Biases in AI Systems: A survey for practitioners
Ramya Srinivasan,Ajay Chander +1 more
TL;DR: In this article, the authors provide an organization of various kinds of biases that can occur in the AI pipeline starting from dataset creation and problem formulation to data analysis and evaluation, highlighting the challenges associated with the design of bias-mitigation strategies and outlining some best practices suggested by researchers.
Patent
Geotagging based on specified criteria
TL;DR: A method of geotagging based on specified criteria is described in this paper, which may include analyzing a data stream indicating a variable parameter associated with an object to determine data within the data stream satisfying a specified criteria.