Results 161 to 170 of about 1,296,537 (338)

Optimizing Interpretable Decision Tree Policies for Reinforcement Learning [PDF]

open access: yesarXiv
Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained increased attention in supervised learning for their inherent interpretability, enabling modelers to understand the ...
arxiv  

Assessing the Ecological Value: Monetizing Process Innovations in Tailored Forming

open access: yesAdvanced Engineering Materials, EarlyView.
This article introduces a method for evaluating the sustainability of innovations, even with limited data. The method is illustrated through an analysis of the “Tailored Forming” technology, which explores the impact of sustainability on economic value added.
Jonas Schneider   +4 more
wiley   +1 more source

Zero-Shot Decision Tree Construction via Large Language Models [PDF]

open access: yesarXiv
This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index.
arxiv  

Simulation of Inhomogeneous Refractive Index Fields Induced by Hot Tailored Forming Components

open access: yesAdvanced Engineering Materials, EarlyView.
This article presents a simulation model for simulating inhomogeneous refractive index fields (IRIF) in hot‐forged components, accounting for thermal influences and complex geometries. Through this simulation, a priori knowledge about the propagation of the IRIF can be obtained, allowing for the positioning of the component or an optical measurement ...
Pascal Kern   +3 more
wiley   +1 more source

Seamless Science: Lifting Experimental Mechanical Testing Lab Data to an Interoperable Semantic Representation

open access: yesAdvanced Engineering Materials, Volume 27, Issue 8, April 2025.
In pursuit of modern data management techniques, this study presents an in‐lab pipeline combining electronic laboratory notebooks (eLabFTW) and Python scripts for creating semantically enriched, interoperable, machine‐actionable data. Automating data mapping enhances usability, collaboration, and unified knowledge representation.
Markus Schilling   +7 more
wiley   +1 more source

High-Speed Processing of the Multispectral Images by Means of Binary Decision Tree

open access: bronze, 1979
Minoru Inamura   +4 more
openalex   +2 more sources

Home - About - Disclaimer - Privacy