Publications related to Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process

Related publications (20)

Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents

This paper investigates the presence of OCR-sensitive neurons within the Transformer architecture and their influence on named entity recognition (NER) performance on historical documents. By analysing neuron activation patterns in response to clean and no ...

Springer Science and Business Media Deutschland GmbH2025

Augmented Carpentry: Integration of Manual Fabrication into the Digital Value Chain

Andrea Settimi

Full robotic automation in construction and digital fabrication has gained significant momentum in the last 20 years. Yet, although effective, these technologies demand considerable capital investment, highly qualified operators, and are often tailored to ...

EPFL2025

On the impact of learning-based image compression on computer vision tasks

Touradj Ebrahimi, Michela Testolina, Evgeniy Upenik

The image compression field is witnessing a shift in paradigm thanks to the rise of neural network-based models. In this context, the JPEG committee is in the process of standardizing the first learning-based image compression standard, known as JPEG AI. W ...

2024

NMR and MS reveal characteristic metabolome atlas and optimize esophageal squamous cell carcinoma early detection

Lijing Xin

Metabolic changes precede malignant histology. However, it remains unclear whether detectable characteristic metabolome exists in esophageal squamous cell carcinoma (ESCC) tissues and biofluids for early diagnosis. Here, we conduct NMR- and MS-based metabo ...

Nature Portfolio2024

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Pascal Fua, Zhen Wei

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

2023

Estimating cross-field particle transport at the outer midplane of TCV by tracking filaments with machine learning

Christian Gabriel Theiler, Davide Galassi, Claudia Colandrea, Curdin Tobias Wüthrich, Nicola Offeddu

Cross-field transport of particles in the boundary region of magnetically confined fusion plasmas is dominated by turbulence. Blobs, intermittent turbulent structures with large amplitude and a filamentary shape appearing in the scrape-off layer (SOL), are ...

IOP Publishing Ltd2023

XTab: Cross-table Pretraining for Tabular Transformers

Mahsa Shoaran, Bingzhao Zhu

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data t ...

JMLR.org2023

Adaptive Robust Data-Driven Building Control via Bilevel Reformulation: An Experimental Result

Colin Neil Jones, Yingzhao Lian, Jicheng Shi, Manuel Pascal Koch

Data-driven control approaches for the minimization of energy consumption of buildings have the potential to significantly reduce deployment costs and increase the uptake of advanced control in this sector. A number of recent approaches based on the applic ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Practice of Streaming Processing of Dynamic Graphs: Concepts, Models, and Systems

Mikhail Kapralov

Graphs processing has become an important part of various areas of computing, including machine learning, medical applications, social network analysis, computational sciences, and others. A growing amount of the associated graph processing workloads are d ...

2023

The nature of carbon deposits and their formation pathways during catalytic supercritical water gasification of glycerol

Christopher Marc Hunston

Supercritical water gasification (SCWG) is a promising technology to convert wet biomass to renewable natural gas. The present study sheds light on the chemical composition and the formation mechanism of coke deposits on a Ru/CNF catalyst during continuous ...

ACADEMIC PRESS INC ELSEVIER SCIENCE2023

COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter

Marcel Salathé, Martin Mathias Müller

IntroductionThis study presents COVID-Twitter-BERT (CT-BERT), a transformer-based model that is pre-trained on a large corpus of COVID-19 related Twitter messages. CT-BERT is specifically designed to be used on COVID-19 content, particularly from social me ...

2023

Modeling, analysis, and design of complex biological networks

Mohammadomid Oftadeh

Automating experimental procedures has resulted in an unprecedented increase in the volume of generated data, which, in turn, has caused an accumulation of unprocessed data. As a result, the need to develop tools to analyze data systematically has been ris ...

EPFL2023

Laser powder bed fusion of Fe-based shape memory alloys for novel structural metamaterials and "smart" structures

Irene Ferretto

Laser powder bed fusion (LPBF) is a powder-based additive manufacturing (AM) technique, which shows great potential in the production of complex-shaped parts with unprecedented design freedom. In addition, it allows for an active manipulation of the micros ...

EPFL2023

Brain signals of a Surprise-Actor-Critic model: Evidence for multiple learning modules in human decision making

Wulfram Gerstner, Johanni Michael Brea, Kerstin Preuschoff, Alireza Modirshanechi, Marco Philipp Lehmann, Vasiliki Liakoni

Learning how to reach a reward over long series of actions is a remarkable capability of humans, and potentially guided by multiple parallel learning modules. Current brain imaging of learning modules is limited by (i) simple experimental paradigms, (ii) e ...

ACADEMIC PRESS INC ELSEVIER SCIENCE2022

Active Learning for Imbalanced Civil Infrastructure Data

Diego Matteo Antognini, Adelmo Cristiano Innocenza Malossi

Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections to support the pr ...

2022

Effect of Y2O3 dispersoids on microstructure and creep properties of Hastelloy X processed by laser powder-bed fusion

Christian Leinenbach

Laser powder bed fusion (LPBF) was used to consolidate powders of a Ni-Cr-Fe-Mo alloy (Hastelloy X) blended with 1 wt% Y2O3 nanometric powders. The nearly-dense, crack-free specimens, with and without oxide dispersion strengthening (ODS), exhibit high-aspe ...

ELSEVIER2022

Perceiving Humans: from Monocular 3D Localization to Social Distancing

Alexandre Massoud Alahi, Sven Kreiss, Lorenzo Bertoni

Perceiving humans in the context of Intelligent Transportation Systems (ITS) often relies on multiple cameras or expensive LiDAR sensors. In this work, we present a new cost-effective vision-based method that perceives humans' locations in 3D and their bod ...

IEEE Institute of Electrical and Electronics Engineers2022

Steel Sheet Sheathed Cold-Formed Steel Framed In-line Wall Systems. II: Impact of Nonstructural Detailing

Fani Derveni

Although cold-formed steel (CFS) framing systems have the potential to support the need for resilient housing, the use of CFS has been restricted due to gaps in understanding its structural behavior and by the limited guidelines provided in design standard ...

ASCE-AMER SOC CIVIL ENGINEERS2022

Low-damage steel structures for enhanced life-cycle seismic performance

Dimitrios Lignos, Martina Paronesso

During an earthquake, steel frame buildings with bracings are prone to high absolute floor acceleration demands, thereby causing damage to acceleration-sensitive non-structural elements and building content. Inelastic deformations in steel bracings and/or ...

ERNST & SOHN2022

Neutron Bragg edge imaging for strain characterization in powder bed additive manufacturing environments

Roland Logé, Reza Esmaeilzadeh, Claire Navarre, Shieren Sumarli

Spatially resolved studies of crystalline structures, e.g. lattice spacings, are enabled by recording the transmitted spectra in neutron Bragg edge imaging. The recorded signals are, however, a result of through-thickness averaging of the probed specimen i ...

ELSEVIER2022