Results 11 to 20 of about 4,047,749 (292)

Model Extraction of Convolutional Neural Networks with Max-Pooling

IACR Transactions on Symmetric Cryptology
Model extraction attacks aim to recover the internal parameters of neural networks through black-box queries. While significant progress has been achieved for fully connected ReLU networks, far less is known about structured architectures such as ...
Haolin Liu, Adrien Siproudhis, Christina Boura, Thomas Peyrin   +3 more
doaj   +3 more sources

Clifford-steerable convolutional neural networks [PDF]

We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of E(p,q)-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces Rp,q.
Weiler, M., Forré, P.D., Lucic, A.; id_orcid, Zhdanov, M., Ruhe, D., Brandstetter, J., Forré, P.   +6 more
core   +7 more sources

Preserving gauge invariance in neural networks [PDF]

EPJ Web of Conferences, 2022
In these proceedings we present lattice gauge equivariant convolutional neural networks (L-CNNs) which are able to process data from lattice gauge theory simulations while exactly preserving gauge symmetry.
Favoni Matteo, Ipp Andreas, Müller David I., Schuh Daniel   +3 more
doaj   +1 more source

Performance Comparison of CNN Models Using Gradient Flow Analysis

Informatics, 2021
Convolutional neural networks (CNNs) are widely used among the various deep learning techniques available because of their superior performance in the fields of computer vision and natural language processing.
Seol-Hyun Noh
doaj   +1 more source

Applications of Lattice Gauge Equivariant Neural Networks [PDF]

EPJ Web of Conferences, 2022
The introduction of relevant physical information into neural network architectures has become a widely used and successful strategy for improving their performance.
Favoni Matteo, Ipp Andreas, Müller David I.   +2 more
doaj   +1 more source

Research on Lane Occupancy Rate Forecasting Based on the Capsule Network

IEEE Access, 2020
This paper proposes a hybrid lane occupancy rate prediction model called 2LayersCapsNet, which combines the improved capsule network and convolutional neural networks (CNNs). The model uses CNNs to mine the spatial-temporal correlation characteristics of
Ran Tian, Jiaming Bi, Qiang Zhang, Yanxing Liu   +3 more
doaj   +1 more source

The use of Convolutional Neural Networks for signal-background classification in Particle Physics experiments [PDF]

EPJ Web of Conferences, 2020
The success of Convolutional Neural Networks (CNNs) in image classification has prompted efforts to study their use for classifying image data obtained in Particle Physics experiments.
Ayyar Venkitesh, Bhimji Wahid, Gerhardt Lisa, Robertson Sally, Ronaghi Zahra   +4 more
doaj   +1 more source

LiteCCLKNet: A lightweight criss‐cross large kernel convolutional neural network for hyperspectral image classification

IET Computer Vision, 2023
High‐performance convolutional neural networks (CNNs) stack many convolutional layers to obtain powerful feature extraction capability, which leads to huge storing and computational costs.
Chengcheng Zhong, Na Gong, Zitong Zhang, Yanan Jiang, Kai Zhang   +4 more
doaj   +1 more source

Lattice gauge equivariant convolutional neural networks

, 2022
We propose Lattice gauge equivariant Convolutional Neural Networks (L-CNNs) for generic machine learning applications on lattice gauge theoretical problems.
Favoni, Matteo; orcid:, Ipp, Andreas; orcid:, Schuh, Daniel; orcid:, Müller, David I.   +3 more
core   +1 more source

Free-Space Optical Neural Network Based on Optical Nonlinearity and Pooling Operations

IEEE Access, 2021
Despite various optical realizations of convolutional neural networks (CNNs), optical implementation of nonlinear activation functions and pooling operations are still challenging problems.
Hoda Sadeghzadeh, Somayyeh Koohi, Ali Fele Paranj   +2 more
doaj   +1 more source