The Scientific Image

By M. Eberhart. 2016

1,415 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b156758e620e7b1b7f600941381141e2978572a7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

Citations in the corpus

Inference to the Best Explanation (IBE) Versus Explaining for the Best Inference (EBI) (2015, background): “Garfinkel (1980) and van Fraassen (1980) both emphasize the role of the contrast class, arguing that we only explain when we have determined why an event happened as opposed to some alternatives stipulated (or implied) in a question.”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “, a set of alternative answers to the given question), and R being the corresponding relevance criteria [13].”
Goals Affect the Perceived Quality of Explanations (2015, background): “For example, van Fraassen (1980) proposes that context fixes the contrast class – that is, the implicit set of possible alternatives to the target observation that the explanation needs to account for – and narrows down the range of relevance relationships that count as explanatory in that context.”
Why Attention is Not Explanation: Surgical Intervention and Causal Reasoning about Neural Models (2020, background): “• The Pragmatic Theory (Van Fraassen, 1977; Van Fraassen, 1980) contrasts itself with logical theories by characterizing explanation not as generation of a particular logical argument structure, and with transmission theories by not requiring the relay of a causal mark.”
Beyond subjective and objective in statistics (2015, background): “For example, the realist ideal of ‘absolute objectivity’ has been branded as metaphysical, meaningless and illusory by positivists including Pearson (1911), and more contemporarily by empiricists such as van Fraassen (1980). The latter took observability and the ability of theory to account for obse”
How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, background): “Several recent XAI reviews have pointedly noted the lack of clear definitions for the notions of explanation, interpretability and transparency [5-10], echoing long-standing discussions in CBR [11, 12], recommender systems [13], Philosophy [14-16] and Psychology [17].”
The explanation game: a formal framework for interpretable machine learning (2020, neutral): “The importance of contrastive explanation is highlighted by several philosophers (Hitchcock 1999; Potochnik 2015; van Fraassen 1980), and has recently begun to receive attention in the iML literature as well (Miller 2019; Mittelstadt et al. 2019).”
Counterfactual Explanations for Machine Learning: A Review (2020, neutral): “of causal thinking due to counterfactuals [17, 114].”
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, neutral): “of causal thinking due to counterfactuals [30, 339].”