What It Means for AI to Understand

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Adedoyin, Ifeoluwa james, NORA Research Lab
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902037376008192
author Adedoyin, Ifeoluwa james
NORA Research Lab
author_facet Adedoyin, Ifeoluwa james
NORA Research Lab
contents <p>This paper explores a fundamental question in artificial intelligence: what does it actually mean for a machine to understand something rather than simply memorize patterns? It introduces a formal framework for distinguishing genuine comprehension from statistical recall using transformation invariance and generalization tests. The paper argues that true understanding is revealed when an AI system can preserve performance across meaningful changes in context, representation, and structure. It further proposes mathematical criteria for evaluating understanding through equivariance and robustness. Beyond intelligence itself, the framework is extended to AI safety and value alignment, showing that capability alone is insufficient without stable alignment to human objectives. The result is a unified theory connecting machine understanding, generalization, and beneficial AI behavior.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_20225147
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle What It Means for AI to Understand
Adedoyin, Ifeoluwa james
NORA Research Lab
Artificial intelligence
Artificial Intelligence
Machine Understanding
Generalization
Memorization vs Understanding
Transformation Invariance
Equivariance
Cognitive Systems
AI Safety
<p>This paper explores a fundamental question in artificial intelligence: what does it actually mean for a machine to understand something rather than simply memorize patterns? It introduces a formal framework for distinguishing genuine comprehension from statistical recall using transformation invariance and generalization tests. The paper argues that true understanding is revealed when an AI system can preserve performance across meaningful changes in context, representation, and structure. It further proposes mathematical criteria for evaluating understanding through equivariance and robustness. Beyond intelligence itself, the framework is extended to AI safety and value alignment, showing that capability alone is insufficient without stable alignment to human objectives. The result is a unified theory connecting machine understanding, generalization, and beneficial AI behavior.</p>
title What It Means for AI to Understand
topic Artificial intelligence
Artificial Intelligence
Machine Understanding
Generalization
Memorization vs Understanding
Transformation Invariance
Equivariance
Cognitive Systems
AI Safety
url https://doi.org/10.5281/zenodo.20225147