The Explanation Game: A Formal Framework for Interpretable Machine Learning

Watson, David S.; Floridi, Luciano

doi:10.1007/978-3-030-81907-1_11

Cited by 10 publications

(7 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In emphasizing that the opacity of such models is not per se a threat to their ability to contribute to explanation and understanding, I do not mean to deny that there are often good reasons to seek transparency. In particular, methods of explainable AI might be used in the process of model validation and in using such models for discovery (Watson and Floridi, 2021;Watson, 2022b).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The Explanatory Role of Machine Learning in Molecular Biology

Gross

2024

Erkenn

View full text Add to dashboard Cite

The philosophical debate around the impact of machine learning in science is often framed in terms of a choice between AI and classical methods as mutually exclusive alternatives involving difficult epistemological trade-offs. A common worry regarding machine learning methods specifically is that they lead to opaque models that make predictions but do not lead to explanation or understanding. Focusing on the field of molecular biology, I argue that in practice machine learning is often used with explanatory aims. More specifically, I argue that machine learning can be tightly integrated with other, more traditional, research methods and in a clear sense can contribute to insight into the causal processes underlying phenomena of interest to biologists. One could even say that machine learning is not the end of theory in important areas of biology, as has been argued, but rather a new beginning. I support these claims with a detailed discussion of a case study involving gene regulation by microRNAs.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This is the goal of the "explainable AI" (xAI) movement, which has received considerable attention (see e.g. Watson and Floridi, 2021;Watson, 2022a;Zednik and Boelsen, 2022;Zerilli, 2022;Beisbart and Räz, 2022;Räz, 2022a), but also generated skeptical reactions (e.g. Rudin, 2019).…”

Section: Machine Learning and The End Of Theorymentioning

confidence: 99%

The Explanatory Role of Machine Learning in Molecular Biology

Gross

2024

Erkenn

View full text Add to dashboard Cite

show abstract

“…As opposed to many works on this topic (but similar to Kasirzadeh et al (2023), Zenil & Bringsjord (2020 among others), this article stresses the important peculiarities of DNNs within ML methods. The present approach has some similarities with the one adopted in Watson and Floridi (2021). Some of the most important differences are: (a) the present focus is on reliability, that naturally leads to consider global, rather than local interpretability; (b) for the same reason, the relevance defined in Watson and Floridi (2021) is less applicable and it is not considered here; (c) finally, Watson and Floridi (2021) consider a subjective notion of simplicity, while we focus on the hardcore complexity that no human can reduce, regardless of language and individual skills.…”

Section: Introductionmentioning

confidence: 89%

Reliability and Interpretability in Science and Deep Learning

Scorzato

2024

Minds & Machines

View full text Add to dashboard Cite

In recent years, the question of the reliability of Machine Learning (ML) methods has acquired significant importance, and the analysis of the associated uncertainties has motivated a growing amount of research. However, most of these studies have applied standard error analysis to ML models—and in particular Deep Neural Network (DNN) models—which represent a rather significant departure from standard scientific modelling. It is therefore necessary to integrate the standard error analysis with a deeper epistemological analysis of the possible differences between DNN models and standard scientific modelling and the possible implications of these differences in the assessment of reliability. This article offers several contributions. First, it emphasises the ubiquitous role of model assumptions (both in ML and traditional science) against the illusion of theory-free science. Secondly, model assumptions are analysed from the point of view of their (epistemic) complexity, which is shown to be language-independent. It is argued that the high epistemic complexity of DNN models hinders the estimate of their reliability and also their prospect of long term progress. Some potential ways forward are suggested. Thirdly, this article identifies the close relation between a model’s epistemic complexity and its interpretability, as introduced in the context of responsible AI. This clarifies in which sense—and to what extent—the lack of understanding of a model (black-box problem) impacts its interpretability in a way that is independent of individual skills. It also clarifies how interpretability is a precondition for a plausible assessment of the reliability of any model, which cannot be based on statistical analysis alone. This article focuses on the comparison between traditional scientific models and DNN models. However, Random Forest (RF) and Logistic Regression (LR) models are also briefly considered.

show abstract

“…Firstly, existing decision modelling and machine learning on irrational behaviour have not taken into account the corresponding decision processes [ 12 ]. While prior research on decision models has simulated the irrational behaviour of individuals, they take the actual outcome of the irrational behaviour as a starting point for modelling and attempt to propose methods to detect, prevent, and/or alleviate undesired bias [ 12 , 13 ]. This approach is unable to describe and model the irrational decision-making process of individuals.…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, they gather as much information as possible and magnify the likelihood of some small probabilities in order to make relatively rational decisions. In this case, some information with a low or medium level of authority will not be able to guide individual behaviour [ 12 , 13 ]. Second, different from other studies on public opinion control in emergencies, this research focuses on a specific type of information in emergencies, that is, the information on individual decision-making and the corresponding actions.…”

Section: Introductionmentioning

confidence: 99%

Fair Transmission of Individual Signals and Formation of Mainstream Information: Evidence from Herd Behaviours in Emergencies

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Risk society is full of emergencies, accompanied by uncertainties and losses. Under emergencies, controlling herd behaviour is challenging due to more interactions and changes among individuals. This research establishes Bayes conditional probability models to explain the fair transmission of individual signals and individual decision-making after receiving others’ signals. The simulation shows the following conclusions: first, each individual has a fair chance to influence the mainstream information; second, the order in which individuals make decisions during an emergency affects the difficulties and likelihood of making a rational decision; third, the high authority of information can become mainstream and guide individual behaviour; and fourth, two individual characteristics, including risk appetite and personal experience, are important in the fair transmission of individual signals and formation of mainstream information. According to the findings, this research proposes two strategies, including interfering with information and controlling existing key opinion leaders to control the mainstream information within a group in emergencies. These two strategies are proved to be useful in detecting and preventing approaches to alleviate individual herd behaviour, which should be monitored and controlled in machine learning models for individual behaviour simulation and prediction. Compared to previous research that focuses on media and public opinion in emergencies, this research focuses on a specific type of information (i.e., individual decision-making and actions) on the individual level and its effects on herd behaviours within the group. This research complements the explanation of the micro-mechanism of how individuals receive information and make decisions and actions.

show abstract

The Explanation Game: A Formal Framework for Interpretable Machine Learning

Cited by 10 publications

References 80 publications

The Explanatory Role of Machine Learning in Molecular Biology

The Explanatory Role of Machine Learning in Molecular Biology

Reliability and Interpretability in Science and Deep Learning

Fair Transmission of Individual Signals and Formation of Mainstream Information: Evidence from Herd Behaviours in Emergencies

Contact Info

Product

Resources

About