A Falsificationist Account of Artificial Neural Networks

The British Journal for the Philosophy of Science (forthcoming)
  Copy   BIBTEX

Abstract

Machine learning operates at the intersection of statistics and computer science. This raises the question as to its underlying methodology. While much emphasis has been put on the close link between the process of learning from data and induction, the falsificationist component of machine learning has received minor attention. In this paper, we argue that the idea of falsification is central to the methodology of machine learning. It is commonly thought that machine learning algorithms infer general prediction rules from past observations. This is akin to a statistical procedure by which estimates are obtained from a sample of data. But machine learning algorithms can also be described as choosing one prediction rule from an entire class of functions. In particular, the algorithm that determines the weights of an artificial neural network operates by empirical risk minimization and rejects prediction rules that lack empirical adequacy. It also exhibits a behavior of implicit regularization that pushes hypothesis choice toward simpler prediction rules. We argue that taking both aspects together gives rise to a falsificationist account of artificial neural networks.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 98,141

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Three Problems with Big Data and Artificial Intelligence in Medicine.Benjamin Chin-Yee & Ross Upshur - 2019 - Perspectives in Biology and Medicine 62 (2):237-256.
Exploring Machine Learning Techniques for Coronary Heart Disease Prediction.Hisham Khdair - 2021 - International Journal of Advanced Computer Science and Applications 12 (5):28-36.
What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
Classification of Real and Fake Human Faces Using Deep Learning.Fatima Maher Salman & Samy S. Abu-Naser - 2022 - International Journal of Academic Engineering Research (IJAER) 6 (3):1-14.
Learnability of state spaces of physical systems is undecidable.Petr Spelda & Vit Stritecky - 2024 - Journal of Computational Science 83 (December 2024):1-7.

Analytics

Added to PP
2022-07-23

Downloads
102 (#179,552)

6 months
33 (#110,418)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

Raidl Eric
University Tübingen

Citations of this work

No citations found.

Add more citations

References found in this work

Two Dogmas of Empiricism.Willard V. O. Quine - 1951 - Philosophical Review 60 (1):20–43.
The Logic of Scientific Discovery.Karl Popper - 1959 - Studia Logica 9:262-265.
A nonpragmatic vindication of probabilism.James M. Joyce - 1998 - Philosophy of Science 65 (4):575-603.
The Aim and Structure of Physical Theory.Pierre Duhem & Philip P. Wiener - 1955 - Science and Society 19 (1):85-87.
Criticism and the Methodology of Scientific Research Programmes.Imre Lakatos - 1969 - Proceedings of the Aristotelian Society 69 (1):149 - 186.

View all 12 references / Add more references