Kolloquium SoSe 2026

Prof. Dr. Özgür Özçep

Universität Hamburg, CHAI

Wann: 04.05.2026, 17:15 Uhr

Wo: Hörsaal 2 (Haus der Informatik)

Thema

Analogical Proportions: Foundations and Applications in Artificial Intelligence

Sprache: English

Abstract

Analogies and analogical reasoning are central topics at the intersection of various disciplines such as computer science (in particular AI), legal reasoning, cognitive science, psychology, and linguistics. This talk focuses on the model of analogical proportions understood as quaternary relations of the form a:b::c:d, read as “a is to b as c is to d.” After presenting recent general results on analogical proportions, the talk discusses their application to concrete instances in two subareas of AI: (1) mechanism design for fair resource allocation and (2) geometry-based knowledge graph embeddings.

Bio

Özgür Lütfü Özçep is a researcher whose work focuses on the foundations of AI, consistently addressing interdisciplinary questions at the intersection of logic, philosophy, cognitive science, and computer science. His current research comprises three main strands. The first is in the broader area of neuro-symbolic AI and concerns the characterization and design of suitable geometric models (such as cones) for embedding concepts. The second lies in the area of logics for common-sense reasoning and focuses on the design and characterization of models for analogical reasoning—in particular, analogical proportions. The third strand is located in the broader field of cooperative AI and addresses the highly interdisciplinary topic of fairness. His recent work examines axiomatizations and mechanisms for fair reward allocation in the case of infinitely replicable resources, such as data or machine learning models, distributed to participants in collaborative learning scenarios. After studying philosophy (earning a Master of Arts degree), he pursued an academic career in computer science. He completed a PhD on belief revision (in the broader area of knowledge representation) and a habilitation on representation theorems in computer science, He owned the title of professorship at the faculty of the Humanities in November 2025. He is currently affiliated with the Institute of Humanities-Centered Artificial Intelligence, which began its work in April 2024 and, since the winter term 2025/26, has offered a master’s degree program titled “Intellectics.” Within Intellectics, he offers courses covering various aspects of logic, agentic AI, and social mechanisms. In particular, he teaches the courses “Agents, Intellectics, and Logics,” “Uncertainty, Causality, and Conditionals,” and “Social Mechanisms, Social Epistemology, and Formal Ethics.”