Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Regneri, Michaela"'
We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationships, we instantiate surface patterns indicating hypernymy and analyze th
Externí odkaz:
http://arxiv.org/abs/2404.15848
Publikováno v:
Second International Workshop on Energy Efficient Scalable Data Mining and Machine Learning (Green Data Mining 2019)
We present an approach to compute the monetary value of individual data points, in context of an automated decision system. The proposed method enables us to explore and implement a paradigm of data minimalism for large-scale machine learning systems
Externí odkaz:
http://arxiv.org/abs/1907.12404
Autor:
Regneri, Michaela, Hoffmann, Malte, Kost, Jurij, Pietsch, Niklas, Schulz, Timo, Stamm, Sabine
Publikováno v:
Proceedings of the 2nd Workshop on Explainable Artificial Intelligence (XAI 2018)
Predictive geometric models deliver excellent results for many Machine Learning use cases. Despite their undoubted performance, neural predictive algorithms can show unexpected degrees of instability and variance, particularly when applied to large d
Externí odkaz:
http://arxiv.org/abs/1807.07404
Autor:
Rohrbach, Marcus, Rohrbach, Anna, Regneri, Michaela, Amin, Sikandar, Andriluka, Mykhaylo, Pinkal, Manfred, Schiele, Bernt
Activity recognition has shown impressive progress in recent years. However, the challenges of detecting fine-grained activities and understanding how they are combined into composite activities have been largely overlooked. In this work we approach
Externí odkaz:
http://arxiv.org/abs/1502.06648
Autor:
Regneri, Michaela
Publikováno v:
Controlling & Management Review; Nov2021, Vol. 65 Issue 8, p28-34, 7p
Autor:
Regneri, Michaela
This thesis proposes new techniques for mining scripts. Scripts are essential pieces of common sense knowledge that contain information about everyday scenarios (like going to a restaurant), namely the events that usually happen in a scenario (enteri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e90d9c58b979517139b9c3e16b648101
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Rohrbach, Marcus, Regneri, Michaela, Andriluka, Mykhaylo, Amin, Sikandar, Pinkal, Manfred, Schiele, Bernt
Publikováno v:
Computer Vision - ECCV 2012 (9783642337178); 2012, p144-157, 14p