Kolloquien und Oberseminare Übersicht Detail

Vortragende Person/Vortragende Personen:
Levin Hornischer

Despite its success, we are lacking a foundational theory of AI. We want to understand and explain the `sub-symbolic' computation performed by
the neural networks that drive this success. For classical `symbolic' computation, this problem was solved by semantics: it mathematically  describes the meaning of program code. In this talk, we work towards an analogous semantics for sub-symbolic computation.

Just like classical computation is specified by program code, we take sub-symbolic computation to be specified by dynamical systems. And just  like classical computation has a denotational interpretation in terms of domains, we provide an adjunction between dynamical systems and
(coalgebras on) domains. The domains are built by observing the systems, and each domain models a system. Finally, just like classical
computation also is specified by a program logic which is Stone dual to the denotational semantics, we provide a program logic for systems based on Boolean algebras with operators.