Benutzerbeiträge von „Vy3326“
1. Dezember 2025
- 09:1709:17, 1. Dez. 2025 Unterschied Versionen +691 Enhancing Trust in Neuro-Symbolic Explanations via Calibrated Linguistic Uncertainty Keine Bearbeitungszusammenfassung aktuell
- 09:1509:15, 1. Dez. 2025 Unterschied Versionen +832 N Enhancing Trust in Neuro-Symbolic Explanations via Calibrated Linguistic Uncertainty Die Seite wurde neu angelegt: „{{Ausschreibung |bearbeitet=Nein |abschlussarbeitstyp=Masterarbeit |betreuer=Nicolas Schuler, Vincenzo Scotti |gruppe=SASIS |pdf=Master Thesis Formalizing and Verifying LLM Based Abductive Reasoning for System Explanations-1.pdf }} Critical AI decision-making demands formally trustworthy explanations. Current neuro-symbolic pipelines use Multimodal Language Models (MLMs) to translate visual data into logic, but often discard valuable uncertainty by forcin…“
- 09:1509:15, 1. Dez. 2025 Unterschied Versionen +607 N Datei:Master Thesis Formalizing and Verifying LLM Based Abductive Reasoning for System Explanations-1.pdf Critical AI decision-making demands formally trustworthy explanations. Current neuro- symbolic pipelines use Multimodal Language Models (MLMs) to translate visual data into logic, but often discard valuable uncertainty by forcing binary decisions. While MLMs natu- rally express confidence through linguistic markers (e.g., ”likely”), these cues remain uncali- brated and unused in reasoning. This thesis aims to bridge this gap by extracting, calibrating, and propagating linguistic uncertainty int… aktuell
- 09:1209:12, 1. Dez. 2025 Unterschied Versionen +586 Towards a Minimal Abductive Reasoning Layer for SASIS Keine Bearbeitungszusammenfassung aktuell
- 09:1009:10, 1. Dez. 2025 Unterschied Versionen +890 N Towards a Minimal Abductive Reasoning Layer for SASIS Die Seite wurde neu angelegt: „{{Ausschreibung |bearbeitet=Nein |abschlussarbeitstyp=Bachelorarbeit |betreuer=Nicolas Schuler, Vincenzo Scotti |gruppe=SASIS |pdf=Bachelor Thesis Towards a Minimal Abductive Reasoning Layer for SASIS.pdf }} Abductive reasoning – inferring the most plausible cause from observed effects – is a pow- erful paradigm for tasks like fault diagnosis and explanation generation. However, classical logic programming tools like Prolog are cumbersome to integra…“
- 09:0809:08, 1. Dez. 2025 Unterschied Versionen +682 N Datei:Bachelor Thesis Towards a Minimal Abductive Reasoning Layer for SASIS.pdf Abductive reasoning – inferring the most plausible cause from observed effects – is a pow- erful paradigm for tasks like fault diagnosis and explanation generation. However, classical logic programming tools like Prolog are cumbersome to integrate into modern software sys- tems, and expertise in these tools is increasingly rare. This thesis explores whether a mini- mal, modular abductive reasoning layer can be designed that integrates easily with existing software engineering frameworks and met… aktuell
10. Oktober 2025
- 12:3012:30, 10. Okt. 2025 Unterschied Versionen +77 Lecture Engineering Self-Adaptive Systems WS 2025/26 add ilias link aktuell
23. September 2025
- 14:1914:19, 23. Sep. 2025 Unterschied Versionen −1 Lecture Engineering Self-Adaptive Systems WS 2025/26 (feat) remove whitespace
- 14:0914:09, 23. Sep. 2025 Unterschied Versionen +1.254 N Lecture Engineering Self-Adaptive Systems WS 2025/26 (feat) add content for lecture