Results 151 to 160 of about 1,259,133 (314)

Abstraction for Bayesian Reinforcement Learning in Factored POMDPs [PDF]

Publisher Copyright: © 2025, Transactions on Machine Learning Research. All rights reserved.Bayesian reinforcement learning provides an elegant solution to addressing the explo-ration–exploitation trade-off in Partially Observable Markov Decision ...
Starre, Rolf A.N., Katt, Sammie, Loog, Marco, Oliehoek, Frans A., Çelikok, Mustafa Mert   +4 more
core  

A scalable hybrid training approach for recurrent spiking neural networks

Neuromorphic Computing and Engineering
Recurrent spiking neural networks (RSNNs) can be implemented very efficiently in neuromorphic systems. Nevertheless, training of these models with powerful gradient-based learning algorithms is mostly performed on standard digital hardware using ...
Maximilian Baronig, Yeganeh Bahariasl, Ozan Özdenizci, Robert Legenstein   +3 more
doaj   +1 more source

Machine learning modularity

CoRR
Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$θ$ function and the elliptic Gamma function.
Yi Fan, Vishnu Jejjala, Yang Lei
openaire   +2 more sources

Towards Defect Phase Diagrams: From Research Data Management to Automated Workflows

Advanced Engineering Materials, EarlyView.
A research data management infrastructure is presented for the systematic integration of heterogeneous experimental and simulation data required for defect phase diagrams. The approach combines openBIS with a companion application for large‐object storage, automated metadata extraction, provenance tracking and federated data access, thereby supporting ...
Khalil Rejiba, Sang‐Hyeok Lee, Christina Gasper, Martina Freund, Sandra Korte‐Kerzel, Ulrich Kerzel   +5 more
wiley   +1 more source

A Knowledge‐Based Approach for Understanding and Managing Additive Manufacturing Data

Advanced Engineering Materials, EarlyView.
Additive manufacturing processes generate a large amount of data. Effectively managing, understanding, and retrieving information from this data remains a major challenge. Therefore, we propose an ontology‐based approach to integrate heterogeneous data, enable semantic queries, and support decision‐making.
Mina Abd Nikooie Pour, Prithwish Tarafder, Anton Wiberg, Huanyu Li, Johan Moverare, Patrick Lambrix   +5 more
wiley   +1 more source

The New Machine Leaming Center at GA Tech: Plans end Aspirations [PDF]

, 2017
Presented at the ML@GT Seminar on March 1, 2017 at 12:00 p.m. in the Marcus Nanotechnology Building, rooms 1117-1118, Georgia Tech.The ML@GT Team also presented at the seminar.Irfan Essa, Associate Dean, is a Professor in the School of Interactive ...
Essa, Irfan
core  

VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Journal of Cheminformatics
We present VN-EGNN, a novel approach to binding site identification that significantly advances predictive performance. By integrating virtual nodes into E(n)– and SE(n)-equivariant graph neural networks (EGNNs) and extending the message-passing scheme ...
Florian Sestak, Lisa Schneckenreiter, Johannes Brandstetter, Sepp Hochreiter, Andreas Mayr, Günter Klambauer   +5 more
doaj   +1 more source

A Simplified Laminar Flow Model for the Pultrusion of Glass Fiber/Polyethylene Terephthalate Commingled Yarns

Advanced Engineering Materials, EarlyView.
A simplified thermoplastic pultrusion model is developed to predict thermal fields in glass fiber/polyethylene terephthalate (GF/PET) composites with reduced computational cost. By combining effective material homogenization, validation against literature data, and Gaussian‐process‐based optimization, the study reveals how heating limits, pulling speed,
Elder Soares, Nadège Bouchonneau, Christian Jochum, Donald Radford   +3 more
wiley   +1 more source

Fostering Innovation: Streamlining Magnetocaloric Materials Research by Digitalization

Advanced Engineering Materials, EarlyView.
Magnetocaloric cooling (MCE) is an environmentally friendly refrigeration method with great potential. Optimizing MCE materials involves the preparation and screening of large quantities of samples, which in turn generates a large amount of data. A digitalization approach is presented that uses ontologies, knowledge graphs, and digital workflows to ...
Simon Bekemeier, Moritz Blum, Luana Caron, Alisa Chirkova, Philipp Cimiano, Basil Ell, Inga Ennen, Michael Feige, Maik Gaerner, Thomas Hilbig, Andreas Hütten, Günter Reiss, Tapas Samanta, Sonja Schöning, Christian Schröder, Lennart Schwan, Chris Taake, Martin Wortmann   +17 more
wiley   +1 more source

Decision processes in 3D structural MRI schizophrenia classification evaluated with saliency maps

Scientific Reports
Clinical decision support systems for psychiatric disorders such as schizophrenia can benefit from machine learning models based on neuroimaging data for objective diagnosis, prognosis, and effective treatment selection. Deep learning (DL) models promise
Julia Jelitzki, Alexandra Reichenbach, Alexander Windberger   +2 more
doaj   +1 more source