Results 51 to 60 of about 113,736 (262)
Transformers are Bayesian Networks
CoRRTransformers are the dominant architecture in AI, yet why they work remains poorly understood. This paper offers a precise answer: a transformer is a Bayesian network. We establish this in five ways. First, we prove that every sigmoid transformer with any weights implements weighted loopy belief propagation on its implicit factor graph.
openaire +2 more sources
Improved learning of Bayesian networks
CoRR, 2001 The search space of Bayesian Network structures is usually defined as Acyclic Directed Graphs (DAGs) and the search is done by local transformations of DAGs. But the space of Bayesian Networks is ordered by DAG Markov model inclusion and it is natural to consider that a good search policy should take this into account.
Kocka, T., Castelo Valdueza, R.
openaire +4 more sources
Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials
Advanced Science, EarlyView.Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan +8 more
wiley +1 more source
Bayesian networks for fMRI: A primer
NeuroImage, 2014 Bayesian network analysis is an attractive approach for studying the functional integration of brain networks, as it includes both the locations of connections between regions of the brain (functional connectivity) and more importantly the direction of the causal relationship between the regions (directed functional connectivity).
Jeanette A. Mumford, Joseph D. Ramsey
openaire +2 more sources
ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals
Advanced Science, EarlyView.The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates efficient remediation strategies. This study presents physics‐informed machine learning workflows that accurately predict critical degradation properties, including bond dissociation energies and polarizability.
Pranoy Ray +3 more
wiley +1 more source
Causality, Propensity, and Bayesian Networks [PDF]
Synthese, 2002 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire +2 more sources
Performance–Complexity Trade‐Offs in Battery Lifetime Prediction with Task‐Aware Transformers
Advanced Science, EarlyView.FAST‐BatPro integrates convolutional feature extraction, flash Attention, and sparse attention for efficient battery lifetime prediction. Using limited early‐cycle data across multiple chemistries and operating conditions, it achieves robust accuracy while reducing inference latency, computational cost, and energy consumption.
Jingyuan Zhao +9 more
wiley +1 more source
Incremental Compilation of Bayesian networks
CoRR, 2003 Most methods of exact probability propagation in Bayesian networks do not carry out the inference directly over the network, but over a secondary structure known as a junction tree or a join tree (JT). The process of obtaining a JT is usually termed {sl compilation}. As compilation is usually viewed as a whole process; each time the network is modified,
Flores, Julia +2 more
openaire +4 more sources
Sustainable Materials Design With Multi‐Modal Artificial Intelligence
Advanced Science, EarlyView.Critical mineral scarcity, high embodied carbon, and persistent pollution from materials processing intensify the need for sustainable materials design. This review frames the problem as multi‐objective optimization under heterogeneous, high‐dimensional evidence and highlights multi‐modal AI as an enabling pathway.
Tianyi Xu +8 more
wiley +1 more source
Comput. Artif. Intell., 1997 Summary: The paper presents a causal-probabilistic approach to the technical diagnosis in which the solution of the technical diagnostic problem is considered as a probabilistic inference on a special kind of Bayesian networks called diagnostic Bayesian networks.
openaire +2 more sources