Results 271 to 280 of about 229,861 (318)

MULTIPURPOSE HYSTERESIS CNN

International Journal of Bifurcation and Chaos, 2004
In this paper, we propose a multipurpose hysteresis CNN (cellular neural network) made of first-order cells with hysteresis switches. The hysteresis CNN has applications not only in image processing, but also in pattern formation, nonlinear wave propagation and associative and dynamic memories, because each hysteresis CNN cell has two operating modes,
Makoto Itoh, Leon O. Chua
openaire   +2 more sources

HYPERCHAOS IN A SIMPLE CNN

International Journal of Bifurcation and Chaos, 2006
In this paper we demonstrate hyperchaotic dynamics in a very simple Cellular Neural Network (CNN) which is a one-dimensional regular array of four cells. The Lyapunov spectrum is calculated in a range of parameters, and the bifurcation plot is presented as well.
Qingdu Li, Xiao-Song Yang, Fangyan Yang
openaire   +1 more source

SP-CNN: A Scalable and Programmable CNN-Based Accelerator

IEEE Micro, 2015
Specialized accelerators have become prevalent in many mobile computing platforms for their ability to perform certain tasks, such as image processing, at a lower power cost than a generalized CPU or GPU. In this article, the authors focus on using cellular neural networks (CNNs) as a specialized accelerator.
Dilan Manatunga, Hyesoon Kim, Saibal Mukhopadhyay   +2 more
openaire   +1 more source

G-CNN and F-CNN: Two CNN based architectures for face recognition

2017 International Conference on Big Data Analytics and Computational Intelligence (ICBDAC), 2017
In the recent past, deployment of Convolutional Neural Networks (CNN) has led to prodigious success in many pattern recognition tasks. This is mainly due to the very nature of CNN, that is its ability to work in a similar manner to that of the visual system of the human brain.
A Vinay, Desanur Naveen Reddy, Abhishek C. Sharma, S Daksha, N S Bhargav, M K Kiran, K N B Murthy, S Natrajan   +7 more
openaire   +1 more source

CNN-SIM: A Detailed Arquitectural Simulator of CNN Accelerators

2020
In this work we provide a quick overview of our ongoing effort to derive an open-source framework for detailed architectural simulation of the inference procedure of CNN hardware accelerators. Our tool, called CNN-SIM, exposes the values computed during the inference procedure of any CNN model using real inputs, which allows the investigation of ...
Francisco Muñoz-Martínez, José L. Abellán, Manuel E. Acacio   +2 more
openaire   +1 more source

The orthogonal CNN problem

Information Processing Letters, 2004
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Kazuo Iwama, Kouki Yonezawa
openaire   +2 more sources

Image compression by CNN

Proceedings of International Conference on Neural Networks (ICNN'96), 2002
This paper presents a very efficient image compression method well suited to the local nature of the CNN Universal Machine. In the case of lossless image compression it outperforms the JPEG image compression standard both in terms of compression efficiency and speed.
Péter L. Venetianer, Tamás Roska
openaire   +1 more source

Decoupled Convolutions for CNNs

Proceedings of the AAAI Conference on Artificial Intelligence, 2018
In this paper, we are interested in designing small CNNs by decoupling the convolution along the spatial and channel domains. Most existing decoupling techniques focus on approximating the filter matrix through decomposition. In contrast, we provide a two-step interpretation of the standard convolution from the filter at a single ...
Guotian Xie, Ting Zhang 0002, Kuiyuan Yang, Jianhuang Lai, Jingdong Wang 0001   +4 more
openaire   +1 more source

Applying CNN to Cheminformatics

2007 IEEE International Symposium on Circuits and Systems (ISCAS), 2007
We describe a method for the construction of specific types of neural networks composed of structures directly linked to the structure of the molecule under consideration. Each molecule can be represented by a unique neural connectivity problem (graph) which can be programmed onto a cellular neural network.
Christian Merkwirth, Maciej Ogorzalek
openaire   +1 more source

The variable neighborhood CNN

ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196), 2002
The cellular neural network (CNN) has been widely used for associative memory. However, it has a problem called indeterminate cell. We describe this problem and propose the variable neighborhood CNN. As a result, we have been able to avoid the problem, and construct a more efficient CNN system for associative memory in simulation.
Michihiro Namba, Shin'ya Takatori, Hiroaki Kawabata, Zhong Zhang   +3 more
openaire   +1 more source