Human Induction in Machine Learning: A Survey of the Nexus

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11230%2F21%3A10427320" target="_blank" >RIV/00216208:11230/21:10427320 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=.w7ubfb2PK" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=.w7ubfb2PK</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3444691" target="_blank" >10.1145/3444691</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Human Induction in Machine Learning: A Survey of the Nexus

Popis výsledku v původním jazyce

As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, then an a posteriori contract comes into effect between humans and the model, supposedly allowing its deployment to target environments. Yet the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The article asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach &quot;elsewhere&quot; in space and time or deploy ML models in non-benign environments. The article argues that the only viable version of the contract can be based on optimality (instead of on reliability, which cannot be justified without circularity) and aligns this position with Schurz&apos;s optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (&quot;elsewhere&quot; and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full.

Název v anglickém jazyce

Human Induction in Machine Learning: A Survey of the Nexus

Popis výsledku anglicky

As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, then an a posteriori contract comes into effect between humans and the model, supposedly allowing its deployment to target environments. Yet the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The article asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach &quot;elsewhere&quot; in space and time or deploy ML models in non-benign environments. The article argues that the only viable version of the contract can be based on optimality (instead of on reliability, which cannot be justified without circularity) and aligns this position with Schurz&apos;s optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (&quot;elsewhere&quot; and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50601 - Political science

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

ACM Computing Surveys

ISSN

0360-0300

e-ISSN

—

Svazek periodika

54

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

18

Strana od-do

1-18

Kód UT WoS článku

000661130600013

EID výsledku v databázi Scopus

2-s2.0-85108104372