Results 81 to 90 of about 204,781 (309)
Self-grouping convolutional neural networks [PDF]
Neural Networks, 2020 Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups
Qingbei Guo +3 more
openaire +4 more sources
Advanced Functional Materials, EarlyView.We use scanning nitrogen vacancy magnetometry to directly image the weak in‐plane magnetic moments in mixed phase BiFeO3 at the nanoscale and quantify the local magnetic moments to be 18.8±2.0 μB/nm2 in the rhombohedral‐like phase and 1.5±0.6 μB/nm2 in the well‐known non‐magnetic tetragonal‐like phase.
Lei Wang +14 more
wiley +1 more source
Spike buffer: improve deep network performance by offset mechanism
The Journal of Engineering, 2020 For a well-designed neural network model, it is difficult to further improve its performance. This study proposes an offset mechanism called spike buffer, which can effectively improve the performance of the designed convolutional neural networks.
Daihui Li, Shangyou Zeng, Chengxu Ma
doaj +1 more source
Analysis and training of a traffic sign recognition neural network model
Вестник Дагестанского государственного технического университета: Технические науки, 2023 Objective. The purpose of the research is to develop and train a neural network model based on convolutional neural networks for effective recognition of road signs in images.Method.
A. U. Mentsiev +2 more
doaj +1 more source
Hyperbolic Convolutional Neural Networks
CoRR, 2023 Deep Learning is mostly responsible for the surge of interest in Artificial Intelligence in the last decade. So far, deep learning researchers have been particularly successful in the domain of image processing, where Convolutional Neural Networks are used.
Andrii Skliar, Maurice Weiler
openaire +2 more sources
Learning shape correspondence with anisotropic convolutional neural networks [PDF]
, 2016 Convolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean ...
Rodolà, Emanuele +4 more
core
CEModule: A Computation Efficient Module for Lightweight Convolutional Neural Networks [PDF]
, 2021 Lightweight convolutional neural networks (CNNs) rely heavily on the design of lightweight convolutional modules (LCMs). For an LCM, lightweight design based on repetitive feature maps (LoR) is currently one of the most effective approaches.
Liang, Y, Li, M, Liu, G, Jiang, C
core +1 more source
Synthesis of AgBiS2 and AgInS2 Based on Formation Energies in Sulfur‐Rich Reducing Flame
Advanced Functional Materials, EarlyView.High‐surface‐area AgInS2 and AgBiS2 nanoparticles were synthesized via enclosed flame spray pyrolysis by tuning flame conditions and formation energies to guide phase formation. Flame parameters were tuned to suppress oxides and enable pure sulfide phase growth.
Muhammad Ali Martuza +7 more
wiley +1 more source
Branching quantum convolutional neural networks
Physical Review Research, 2022 Neural-network-based algorithms have garnered considerable attention for their ability to learn complex patterns from very-high-dimensional data sets towards classifying complex long-range patterns of entanglement and correlations in many-body quantum ...
Ian MacCormack +4 more
doaj +1 more source
Computation, 2023 Convolutional neural networks (CNNs) are one of the main types of neural networks used for image recognition and classification. CNNs have several uses, some of which are object recognition, image processing, computer vision, and face recognition.
Mohammad Mustafa Taye
doaj +1 more source