Zobrazeno 1 - 10
of 916
pro vyhledávání: '"Network compression"'
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-16 (2024)
Abstract This paper proposes a geometric-based technique for compressing convolutional neural networks to accelerate computations and improve generalization by eliminating non-informative components. The technique utilizes a geometric index called se
Externí odkaz:
https://doaj.org/article/0c04483c62b142d5b1b8fc5194aa6671
Publikováno v:
Proceedings on Engineering Sciences, Vol 6, Iss 2, Pp 439-452 (2024)
Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer (DHT) mod
Externí odkaz:
https://doaj.org/article/3d806aa1822641faa072e6e426354e25
Autor:
Pragnesh Thaker, Biju R. Mohan
Publikováno v:
IEEE Access, Vol 12, Pp 172537-172547 (2024)
Transfer learning models tackle two critical problems in deep learning. First, for small datasets, it reduces the problem of overfitting. Second, for large datasets, it reduces the computational cost as fewer iterations are required to train the mode
Externí odkaz:
https://doaj.org/article/068852194fc44fd884860f48a6a59a85
Publikováno v:
IEEE Access, Vol 12, Pp 159611-159621 (2024)
With the development of deep learning and graphics processing units (GPUs), various convolutional neural network (CNN)-based computer vision studies have been conducted. Because numerous computations are involved in the inference and training process
Externí odkaz:
https://doaj.org/article/30b8b56179be4b2a9f01709df17fed9e
Autor:
Lingyun Zhou, Xiaoyong Liu
Publikováno v:
IEEE Access, Vol 12, Pp 136925-136935 (2024)
Filter pruning is a potent technique for diminishing the computational demands of Convolutional Neural Networks (CNNs), while effectively retaining model performance in image categorization tasks. However, research on its application to object detect
Externí odkaz:
https://doaj.org/article/b6fbded8ea804a0693e9dad921788442
Publikováno v:
IEEE Access, Vol 12, Pp 123771-123781 (2024)
Owing to improvements in computing power, deep learning technology using convolutional neural networks (CNNs) has recently been used in various fields. However, using CNNs on edge devices is challenging because of the large computation required to ac
Externí odkaz:
https://doaj.org/article/63cfae2d75234feca5dd66f837b0d494
Autor:
Pragnesh Thaker, Biju R. Mohan
Publikováno v:
IEEE Access, Vol 12, Pp 94914-94925 (2024)
This research paper delves into the challenges associated with deep learning models, specifically focusing on transfer learning. Despite the effectiveness of widely used models such as VGGNet, ResNet, and GoogLeNet, their deployment on resource-const
Externí odkaz:
https://doaj.org/article/e45c645f1caf4c91bc29eae38e469b3a
Autor:
Simegnew Yihunie Alaba, John E. Ball
Publikováno v:
IEEE Access, Vol 12, Pp 50165-50176 (2024)
Accurate 3D object detection is vital for autonomous driving since it facilitates accurate perception of the environment through multiple sensors. Although cameras can capture detailed color and texture features, they have limitations regarding depth
Externí odkaz:
https://doaj.org/article/bc10e9c624214157af567889c08f2855
Publikováno v:
IEEE Access, Vol 12, Pp 37276-37287 (2024)
When implementing a super-resolution (SR) model on an edge device, it is common to train the model on a cloud using pre-determined training images. This is due to the lack of large-scale training data and computation power available on the edge devic
Externí odkaz:
https://doaj.org/article/e66110960ac6460585bab5fa5c07297f
Publikováno v:
Symmetry, Vol 16, Iss 11, p 1461 (2024)
Rolling bearings are often exposed to high speeds and pressures, leading to the symmetry in their rotating structure being disrupted, which can lead to serious failures. Intelligent rolling bearing fault diagnosis is a critical part of ensuring opera
Externí odkaz:
https://doaj.org/article/b8700c4ade6a46d6828c1edcfee330e5