Results 211 to 220 of about 140,076 (268)
Feature stabilization in convolutional neural networks using Proportional Integral Controller for lung nodule classification. [PDF]
Front Artif IntellSangeetha V, Kalaivani S.
europepmc +1 more source
Deep Learning Discriminates Seizures from Normal Brain Oscillations in the Electroencephalogram of a Rat Model of Post-traumatic Epilepsy. [PDF]
eNeuroTatum S +9 more
europepmc +1 more source
DeepForgeryNet: a hybrid CNN-LSTM and transfer learning framework for robust image forgery and deepfake detection. [PDF]
Front Artif IntellSardhara A +3 more
europepmc +1 more source
In Silico Studies of Potent Tyrosine Kinase Inhibitors: Molecular Docking and Pharmacophore Modeling Approaches. [PDF]
MoleculesMavridis E +2 more
europepmc +1 more source
A wearable IMU-based framework for daily physical activity recognition and energy expenditure level classification in university students. [PDF]
Front Public HealthZhou X, Wang S, He L, Ma L.
europepmc +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Teaching CNN and learning by using CNN
Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications, 2003In this communication we remark our experience in teaching CNN technologies at the Universita degli Studi di Catania in the course of Adaptive Systems. The main result regards the possibility of using the CNN subject to introduce further topics in circuits and dynamical systems. The students reached high level skills in the related field. Moreover they
BUCOLO, MAIDE ANGELA RITA +3 more
openaire +3 more sources
IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 1993
A concise tutorial description of the cellular neural network (CNN) paradigm is given, along with a precise taxonomy. The CNN is defined, and the canonical equations are described. The importance of many independent input signal arrays, adaptive templates, and the multilayer capability is emphasized and motivated by examples.
Chua, Leon O., Roska, Tamás
openaire +2 more sources
A concise tutorial description of the cellular neural network (CNN) paradigm is given, along with a precise taxonomy. The CNN is defined, and the canonical equations are described. The importance of many independent input signal arrays, adaptive templates, and the multilayer capability is emphasized and motivated by examples.
Chua, Leon O., Roska, Tamás
openaire +2 more sources
2023
The field of artificial intelligence (AI) is very promising with the emergence of machine learning and deep learning algorithms. The rise of convolutional neural networks (CNN) is very propitious in deep learning as it is more accurate and powerful than previously known soft computational models like artificial neural networks (ANN) and recurrent ...
Mohan Kumar Dehury +2 more
openaire +1 more source
The field of artificial intelligence (AI) is very promising with the emergence of machine learning and deep learning algorithms. The rise of convolutional neural networks (CNN) is very propitious in deep learning as it is more accurate and powerful than previously known soft computational models like artificial neural networks (ANN) and recurrent ...
Mohan Kumar Dehury +2 more
openaire +1 more source
Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94, 2002
If a CNN template, through the application of one of the sign-changing transformations T defined by Chua and Wu (see Int. Journal of Circuit Theory and Applications, vol. 20, p.497-517, 1992), is positive and cell-linking and has isolated equilibria then the convergence of the original CNN follows; this is theorem 4 of the aforementioned paper.
Mark P. Joy, Vedat Tavsanoglu
openaire +1 more source
If a CNN template, through the application of one of the sign-changing transformations T defined by Chua and Wu (see Int. Journal of Circuit Theory and Applications, vol. 20, p.497-517, 1992), is positive and cell-linking and has isolated equilibria then the convergence of the original CNN follows; this is theorem 4 of the aforementioned paper.
Mark P. Joy, Vedat Tavsanoglu
openaire +1 more source