Federated Repair of Deep Neural Networks
As DNNs are embedded in more and more critical systems, it is essential to ensure that they
perform well on specific inputs. DNN repair has shown good results in fixing specific …
perform well on specific inputs. DNN repair has shown good results in fixing specific …
The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines
Although database systems perform well in data access and manipulation, their relational
model hinders data scientists from formulating machine learning algorithms in SQL …
model hinders data scientists from formulating machine learning algorithms in SQL …
The Duck's Brain: Training and Inference of Neural Networks within Database Engines
Although database systems perform well in data access and manipulation, their relational
model hinders data scientists from formulating machine learning algorithms in SQL …
model hinders data scientists from formulating machine learning algorithms in SQL …
[PDF][PDF] Secondary Publication
ABSTRACT AI-based technologies have changed the nature of the symbiosis between
humans and AI, and so strategic management of human-AI interaction in organizations …
humans and AI, and so strategic management of human-AI interaction in organizations …
Improving Prototypical Parts Abstraction for Case-Based Reasoning Explanations Designed for the Kidney Stone Type Recognition
D Flores-Araiza, F Lopez-Tiro, C Larose… - arXiv preprint arXiv …, 2024 - arxiv.org
The in-vivo identification of the kidney stone types during an ureteroscopy would be a major
medical advance in urology, as it could reduce the time of the tedious renal calculi extraction …
medical advance in urology, as it could reduce the time of the tedious renal calculi extraction …
Integration of web scraping, fine-tuning, and data enrichment in a continuous monitoring context via large language model operations.
This paper presents and discusses a framework that leverages large-scale language
models (LLMs) for data enrichment and continuous monitoring emphasizing its essential …
models (LLMs) for data enrichment and continuous monitoring emphasizing its essential …
Towards a Peer-to-Peer Data Distribution Layer for Efficient and Collaborative Resource Optimization of Distributed Dataflow Applications
Performance modeling can help to improve the resource efficiency of clusters and
distributed dataflow applications, yet the available modeling data is often limited …
distributed dataflow applications, yet the available modeling data is often limited …
Algorithmic assessment of drag on thermally cut sheet metal edges
J Stahl, S Zengl, A Frommknecht, C Jauch… - tm-Technisches …, 2024 - degruyter.com
Drag is a key criterion in assessing the quality of thermally cut sheet metal edges, which is
critical to the reliability of the final product. The evaluation of drag has been described …
critical to the reliability of the final product. The evaluation of drag has been described …
[PDF][PDF] Methods for the adaptive provisioning of resources to iterative batch jobs
D Scheinert - 2024 - depositonce.tu-berlin.de
In light of continuously growing amounts of data as well as the proliferation of machine
learning use cases, batch processing of data remains an important procedure. Batch …
learning use cases, batch processing of data remains an important procedure. Batch …