Results 41 to 50 of about 73,468 (309)

Empirical Remarks on the Translational Equivariance of Convolutional Layers

Applied Sciences, 2020
In general, convolutional neural networks (CNNs) maintain some level of translational invariance. However, the convolutional layer itself is translational-equivariant. The pooling layers provide some level of invariance. In object recognition, invariance
Kyung Joo Cheoi, Hyeonyeong Choi, Jaepil Ko   +2 more
doaj   +1 more source

Application of Convolutional Neural Network (CNN) to Recognize Ship Structures

Sensors, 2022
The purpose of this paper is to study the recognition of ships and their structures to improve the safety of drone operations engaged in shore-to-ship drone delivery service. This study has developed a system that can distinguish between ships and their structures by using a convolutional neural network (CNN).
Jae-Jun Lim, Dae-Won Kim, Woon-Hee Hong, Min Kim, Dong-Hoon Lee, Sun-Young Kim, Jae-Hoon Jeong   +6 more
openaire   +4 more sources

Gradient-Based Pooling for Convolutional Neural Networks [PDF]

, 2019
Pooling layers are an important part of convolutional neural networks (CNNs). They reduce the dimensionality of feature maps and pass salient information to subsequent layers. In this paper, we introduce a novel gradient-based feature pooling method that
Gao, Y, Jun Zhou, Mohammad Nikzad, Nikzad, M, Zhou, J, Yongsheng Gao   +5 more
core   +1 more source

Powerset convolutional neural networks [PDF]

, 2019
We present a novel class of convolutional neural networks (CNNs) for set functions,i.e., data indexed with the powerset of a finite set. The convolutions are derivedas linear, shift-equivariant functions for various notions of shifts on set functions.The
Püschel, Markus, Wendler, Chris, Alistarh, Dan-Adrian ; https://orcid.org/   +2 more
core   +2 more sources

Fine Tuning Hyperparameters of Deep Learning Models Using Metaheuristic Accelerated Particle Swarm Optimization Algorithm

IEEE Access
In recent years, Convolutional Neural Networks (CNNs) have emerged as powerful tools for solving complex real-world problems, particularly in the domain of image processing.
Abdel-Hamid M. Emara, Ghada Atteia, Jawad Hasan Alkhateeb   +2 more
doaj   +1 more source

YOLO Network with a Circular Bounding Box to Classify the Flowering Degree of Chrysanthemum

AgriEngineering, 2023
Detecting objects in digital images is challenging in computer vision, traditionally requiring manual threshold selection. However, object detection has improved significantly with convolutional neural networks (CNNs), and other advanced algorithms, like
Hee-Mun Park, Jin-Hyun Park
doaj   +1 more source

AAR-CNNs: Auto Adaptive Regularized Convolutional Neural Networks [PDF]

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018
In order to address the overfitting problem caused by the small or simple training datasets and the large model’s size in Convolutional Neural Networks (CNNs), a novel Auto Adaptive Regularization (AAR) method is proposed in this paper. The relevant networks can be called AAR-CNNs. AAR is the first method using the “abstraction extent” (predicted by AE
Yao Lu 0008, Guangming Lu 0002, Yuanrong Xu, Bob Zhang 0001   +3 more
openaire   +1 more source

Convolutional Neural Network (CNN) with Randomized Pooling

, 2022
Abstract Convolutional Neural Network (CNN) is a deep learning approach to solve complex problems, and it has been widely used in image processing for image classification, object identification, semantic segmentation etc. It has overcome the constraint of traditional machine learning approaches.
Hafiz Imran, Khalid Aamir, Muhammad Ilyas   +2 more
openaire   +1 more source

Enhancing Breast Cancer Detection through Ultrasound Images using Convolutional Neural Networks (CNNs) [PDF]

, 2023
This study showcases Convolutional Neural Networks' (CNNs) potential in detecting breast cancer from ultrasound images. Impressive accuracy highlights their value in precise and efficient diagnosis, paving the way for further research.
Dheiver Francisco Santos (15733274)
core   +1 more source

Fixed point actions from convolutional neural networks [PDF]

Lattice gauge-equivariant convolutional neural networks (L-CNNs) can be used to form arbitrarily shaped Wilson loops and can approximate any gauge-covariant or gauge-invariant function on the lattice.
Holland, K., Wenger, U., Ipp, A., Müller, D. I.   +3 more
core   +1 more source