The architecture of object-based attention
P Cavanagh, GP Caplovitz, TK Lytchenko… - Psychonomic Bulletin & …, 2023 - Springer
The allocation of attention to objects raises several intriguing questions: What are objects,
how does attention access them, what anatomical regions are involved? Here, we review …
how does attention access them, what anatomical regions are involved? Here, we review …
Deep learning, machine learning and internet of things in geophysical engineering applications: An overview
Abstract The earthquakes in Eastern Mediterranean are mostly tectonic. The earthquakes
that are 60 km deep in the ground are called Shallow earthquakes. The earthquakes in the …
that are 60 km deep in the ground are called Shallow earthquakes. The earthquakes in the …
Deep learning in vision-based static hand gesture recognition
OK Oyedotun, A Khashman - Neural Computing and Applications, 2017 - Springer
Hand gesture for communication has proven effective for humans, and active research is
ongoing in replicating the same success in computer vision systems. Human–computer …
ongoing in replicating the same success in computer vision systems. Human–computer …
Non-intrusive surrogate modeling for parametrized time-dependent partial differential equations using convolutional autoencoders
This paper presents a novel non-intrusive surrogate modeling scheme based on deep
learning for predictive modeling of complex systems, described by parametrized time …
learning for predictive modeling of complex systems, described by parametrized time …
Application of deep learning in neuroradiology: brain haemorrhage classification using transfer learning
AM Dawud, K Yurtkan… - Computational Intelligence …, 2019 - Wiley Online Library
In this paper, we address the problem of identifying brain haemorrhage which is considered
as a tedious task for radiologists, especially in the early stages of the haemorrhage. The …
as a tedious task for radiologists, especially in the early stages of the haemorrhage. The …
Gaze prediction based on convolutional neural network
In this paper gaze prediction aims to acquire good performance via “Convolutional Neural
Network (CNN)” based identification. Gaze prediction was proposed to localize the gaze …
Network (CNN)” based identification. Gaze prediction was proposed to localize the gaze …
A deep feature extraction approach for bearing fault diagnosis based on multi-scale convolutional autoencoder and generative adversarial networks
Z Hu, T Han, J Bian, Z Wang, L Cheng… - Measurement …, 2022 - iopscience.iop.org
The vibration signal of a bearing is closely related to its fault. The quality of the features
extracted from the signal has a great impact on the accuracy of fault diagnosis. In this paper …
extracted from the signal has a great impact on the accuracy of fault diagnosis. In this paper …
Daqn: Deep auto-encoder and q-network
D Kimura - arXiv preprint arXiv:1806.00630, 2018 - arxiv.org
The deep reinforcement learning method usually requires a large number of training images
and executing actions to obtain sufficient results. When it is extended a real-task in the real …
and executing actions to obtain sufficient results. When it is extended a real-task in the real …
Non-intrusive surrogate modeling for parametrized time-dependent PDEs using convolutional autoencoders
S Nikolopoulos, I Kalogeris… - arXiv preprint arXiv …, 2021 - arxiv.org
This work presents a non-intrusive surrogate modeling scheme based on machine learning
technology for predictive modeling of complex systems, described by parametrized time …
technology for predictive modeling of complex systems, described by parametrized time …
A simple and practical review of over-fitting in neural network learning
OK Oyedotun, EO Olaniyi… - International Journal of …, 2017 - inderscienceonline.com
Training a neural network involves the adaptation of its internal parameters for modelling a
specific task. The states of the internal parameters during training describe how much …
specific task. The states of the internal parameters during training describe how much …