Toward Out-of-Distribution Generalization Through Inductive Biases

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

MORUZZI, Caterina, 2022. Toward Out-of-Distribution Generalization Through Inductive Biases. In: MÜLLER, Vincent C., ed.. Philosophy and Theory of Artificial Intelligence 2021. Cham:Springer. ISBN 978-3-031-09152-0

@incollection{Moruzzi2022Towar-57918, title={Toward Out-of-Distribution Generalization Through Inductive Biases}, year={2022}, number={63}, isbn={978-3-031-09152-0}, address={Cham}, publisher={Springer}, series={Studies in Applied Philosophy, Epistemology and Rational Ethics}, booktitle={Philosophy and Theory of Artificial Intelligence 2021}, editor={Müller, Vincent C.}, author={Moruzzi, Caterina} }

2022-07-04T07:01:55Z Moruzzi, Caterina State-of-the-art Machine Learning systems are able to process and analyze a large amount of data but they still struggle to generalize to out-of-distribution scenarios. To use Judea Pearl’s words, “Data are profoundly dumb" (Pearl&Mackenzie, 2018); possessing a model of the world, a representation through which to frame reality is a necessary requirement in order to discriminate between relevant and irrelevant information and to deal with unknown scenarios. The aim of this paper is to address the crucial challenge of out-of-distribution generalization in automated systems by developing an understanding of how human agents build models to act in a dynamic environment. The steps needed to reach this goal are described by Pearl through the metaphor of the Ladder of Causation. In this paper, I support the relevance of inductive biases in order for an agent to reach the second rung on the Ladder: that of actively interacting with the environment. Moruzzi, Caterina 2022-07-04T07:01:55Z 2022 eng Toward Out-of-Distribution Generalization Through Inductive Biases terms-of-use

This item appears in the following Collection(s)

Search KOPS


My Account