Understanding and explanation: Living apart together?

Regt, Henk W. de

doi:10.1016/j.shpsa.2012.12.002

Cited by 11 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, philosophers of science have become more interested in the notion of understanding (see De Regt, Leonelli &Eigner 2009 andDe Regt 2013 for good overviews). Understanding is supposed to be the result of successful explanation, but it may also be available from other sources, such as visual models (Lipton 2009) or unification (Gijsbers 2013).…”

Section: Introductionmentioning

confidence: 99%

Is a coherence theory of understanding possible?

Gijsbers

2015

THEORIA

View full text Add to dashboard Cite

Coherence is a measure of how much our beliefs hang together. Understanding is achieved when we see that something is not just a brute, isolated fact. This suggests that it might be possible to use the extant probabilistic measures of coherence to formulate a measure of understanding. We attempt to do so, but it turns out that a coherence theory runs into trouble with the asymmetry of understanding. We identify four difficulties and show how they have been solved by a unification approach to explanation. We also identify four advantages of the coherence approach, and assess the possibilities of reconciling the strengths of the two approaches.Keywords: coherence, understanding, explanation, unification, asymmetry RESUMEN: La coherencia es una medida sobre cuánta interdependencia hay entre nuestras creencias. La comprensión se obtiene cuando vemos que algo no es un hecho bruto, aislado. Esto sugiere la posibilidad de usar las medidas probabilísticas de coherencia al uso para elaborar una medida de la comprensión. Exploraré esta posibilidad, a pesar de que una teoría de la coherencia tropieza con problemas aquí dado el carácter asimétrico de la comprensión. Identifico cuatro dificultades al respecto y muestro cómo han sido resueltas mediante un enfoque de la explicación basado en la noción de unificación. También identifico cuatro ventajas en la aproximación desde la coherencia y examino qué perspectivas hay de reconciliar los puntos fuertes de ambos planteamientos.

show abstract

Section: Introductionmentioning

confidence: 99%

Is a coherence theory of understanding possible?

Gijsbers

2015

THEORIA

View full text Add to dashboard Cite

show abstract

“…What I say here does not commit me to taking a side in the ongoing debate as to whether understanding is a cognitive achievement in its own right, or whether it is a side‐effect of scientific explanation (see de Regt ). Some, like Strevens (: 3; : 510), hold that “an individual has scientific understanding of a phenomenon just in case they grasp a correct scientific explanation of that phenomenon.” Others, like Lipton (), hold that understanding and explanation should be distinguished: understanding is the cognitive benefit that explanation provides, rather than the explanation itself.…”

mentioning

confidence: 98%

How to Understand the Extended Mind

Bernecker

2014

Philosophical Issues

View full text Add to dashboard Cite

show abstract

“…For discussion pertaining to objective vs. subjective understanding, see (H. W de Regt, 2009de Regt, , 2013Grimm, 2010;Lipton, 2009;Strevens, 2013)(Gijsbers, 2007;Shaffer, 2020).…”

mentioning

confidence: 99%

ANNs and Unifying Explanations: Reply to Erasmus, Brunet, and Fisher

Prasetya

2022

Philos. Technol.

View full text Add to dashboard Cite

In a recent article, Erasmus, Brunet, and Fisher (2021) argue that Artificial Neural Networks (ANNs) are explainable. They survey four influential accounts of explanation: the Deductive-Nomological model, the Inductive-Statistical model, the Causal-Mechanical model, and the New-Mechanist model. They argue that, on each of these accounts, the features that make something an explanation is invariant with regard to the complexity of the explanans and the explanandum. Therefore, they conclude, the complexity of ANNs (and other Machine Learning models) does not make them less explainable. In this reply, it is argued that Erasmus et al. left out one influential account of explanation from their discussion: the unificationist model. It is argued that, on the unificationist model, the features that make something an explanation is sensitive to complexity. Therefore, on the unificationist model, ANNs (and other Machine Learning models) are not explainable.It is emphasized that Erasmus et al.'s general strategy is correct. The literature on explainable Artificial Intelligence can benefit by drawing from philosophical accounts of explanation. However, philosophical accounts of explanation do not settle the problem of whether ANNs are explainable because they do not unanimously declare that explanation is invariant with regard to complexity.

show abstract

Understanding and explanation: Living apart together?

Cited by 11 publications

References 11 publications

Is a coherence theory of understanding possible?

Is a coherence theory of understanding possible?

How to Understand the Extended Mind

ANNs and Unifying Explanations: Reply to Erasmus, Brunet, and Fisher

Contact Info

Product

Resources

About