Results 1 to 10 of about 71,812 (118)
Generative Modeling for Interpretable Anomaly Detection in Medical Imaging: Applications in Failure Detection and Data Curation [PDF]
BioengineeringThis work aims to leverage generative modeling-based anomaly detection to enhance interpretability in AI failure detection systems and to aid data curation for large repositories.
McKell E. Woodland +12 more
doaj +2 more sources
Applied Mechanics, 2023 Advanced Driver Assistance Systems (ADASs) attract constantly growing attention from academics and industry as more and more vehicles are equipped with such technology.
Zafer Kayatas +3 more
doaj +1 more source
Deep Neural Networks in Power Systems: A Review
Energies, 2023 Identifying statistical trends for a wide range of practical power system applications, including sustainable energy forecasting, demand response, energy decomposition, and state estimation, is regarded as a significant task given the rapid expansion of ...
Mahdi Khodayar, Jacob Regan
doaj +1 more source
Active Vision for Robot Manipulators Using the Free Energy Principle
Frontiers in Neurorobotics, 2021 Occlusions, restricted field of view and limited resolution all constrain a robot's ability to sense its environment from a single observation. In these cases, the robot first needs to actively query multiple observations and accumulate information ...
Toon Van de Maele +4 more
doaj +1 more source
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
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
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
Model Reduction Through Progressive Latent Space Pruning in Deep Active Inference
Frontiers in Neurorobotics, 2022 Although still not fully understood, sleep is known to play an important role in learning and in pruning synaptic connections. From the active inference perspective, this can be cast as learning parameters of a generative model and Bayesian model ...
Samuel T. Wauthier +4 more
doaj +1 more source
Multimodal Sensor Fusion Using Symmetric Skip Autoencoder Via an Adversarial Regulariser
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021 The fusion of the spatial characteristics, of visual image, and spectral aspects, of infrared image, is of immense practical importance. In this work, we propose a novel spatially constrained adversarial autoencoder that extracts deep features from the ...
Snigdha Bhagat +3 more
doaj +1 more source