Algorithmic Randomness

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

Continuous randomness via transformations of 2-random sequences

Porter¹

2023

Information and Computation

View full text Add to dashboard Cite

Algorithmic Randomness

Abstract: In this article we present the framework of layerwise computability. We explain the origin of this notion, its main features and properties, and we illustrate it with several concrete examples: decomposition of measures, random closed sets, Brownian motion.

Cited by 7 publications

References 14 publications

Extraction Rates of Random Continuous Functionals

Extraction Rates of Random Continuous Functionals

Reliability and Interpretability in Science and Deep Learning

Continuous randomness via transformations of 2-random sequences

Contact Info

Product

Resources

About