Results 31 to 40 of about 65,539 (306)
Disentangling Generative Factors of Physical Fields Using Variational Autoencoders
Frontiers in Physics, 2022 The ability to extract generative parameters from high-dimensional fields of data in an unsupervised manner is a highly desirable yet unrealized goal in computational physics.
Christian Jacobsen, Karthik Duraisamy
doaj +1 more source
A Generic Model of Consciousness
Journal of Artificial Intelligence and Consciousness, 2023 This is a model of consciousness. The hard problem of consciousness, what it feels like, is answered. The work builds on medical research analyzing the source and mechanisms associated with our feelings. It goes further by describing a generic model with wide applicability.
openaire +2 more sources
Semi-Supervised Source Localization in Reverberant Environments With Deep Generative Modeling
IEEE Access, 2021 Localization in reverberant environments remains an open challenge. Recently, supervised learning approaches have demonstrated very promising results in addressing reverberation.
Michael J. Bianco +3 more
doaj +1 more source
SDF4CHD: Generative modeling of cardiac anatomies with congenital heart defects [PDF]
Medical Image AnalysisFanwei Kong, Perry S Choi, Michael Ma
exaly +2 more sources
Embodied Object Representation Learning and Recognition
Frontiers in Neurorobotics, 2022 Scene understanding and decomposition is a crucial challenge for intelligent systems, whether it is for object manipulation, navigation, or any other task.
Toon Van de Maele +3 more
doaj +1 more source
Cells, 2022 Design and generation of high-quality target- and scaffold-specific small molecules is an important strategy for the discovery of unique and potent bioactive drug molecules.
Yuemin Bian, Xiang-Qun Xie
doaj +1 more source
Generative Marginalization Models
CoRR, 2023 We introduce marginalization models (MAMs), a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distributions. Marginalization models enable fast approximation of arbitrary marginal probabilities with a single forward pass of the neural ...
Sulin Liu +2 more
openaire +3 more sources
A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability
IEEE Access, 2019 When failure data are limited, data-driven prognostics solutions underperform since the number of failure data samples is insufficient for training prognostics models effectively.
Gishan D. Ranasinghe +3 more
doaj +1 more source
On the Generalization of Diffusion Model
CoRR, 2023 The diffusion probabilistic generative models are widely used to generate high-quality data. Though they can synthetic data that does not exist in the training set, the rationale behind such generalization is still unexplored. In this paper, we formally define the generalization of the generative model, which is measured by the mutual information ...
Mingyang Yi, Jiacheng Sun, Zhenguo Li
openaire +2 more sources