CST – Computer Simulation Technology

Fixed Weight Hopfield Neural Network Based on Optical Implementation of All-Optical MZI-XNOR Logic Gate
Kussay Nugamesh Mutter, Mohd Zubir Mat Jafri, Azlan Abdul Aziz
Volume: 7717, 14 May 2010
Hopfield Neural Network, Self-connection architecture, Mach-Zehnder Interferometer, XOR, XNOR logic gates
Many researches are conducted to improve Hopfield Neural Network (HNN) performance especially for speed and memory capacity in different approaches. However, there is still a significant scope of developing HNN using Optical Logic Gates. We propose here a new model of HNN based on all-optical XNOR logic gates for real time color image recognition. Firstly, we improved HNN toward optimum learning and converging operations. We considered each unipolar image as a set of small blocks of 3-pixels as vectors for HNN. This enables to save large number of images in the net with best reaching into global minima, and because there are only eight fixed states of weights so that only single iteration performed to construct a vector with stable state at minimum energy. HNN is useless in dealing with data not in bipolar representation. Therefore, HNN failed to work with color images. In RGB bands each represents different values of brightness, for d-bit RGB image it is simply consists of d-layers of unipolar. Each layer is as a single unipolar image for HNN. In addition, the weight matrices with stability of unity at the diagonal perform clear converging in comparison with no self-connecting architecture. Synchronously, each matrix-matrix multiplication operation would run optically in the second part, since we propose an array of all-optical XOR gates, which uses Mach-Zehnder Interferometer (MZI) for neurons setup and a controlling system to distribute timely signals with inverting to achieve XNOR function. The primary operation and simulation of the proposal HNN is demonstrated.

Back to References

contact support

Your session has expired. Redirecting you to the login page...

We use cookie to operate this website, improve its usability, personalize your experience, and track visits. By continuing to use this site, you are consenting to use of cookies. You have the possibility to manage the parameters and choose whether to accept certain cookies while on the site. For more information, please read our updated privacy policy

Cookie Management

When you browse our website, cookies are enabled by default and data may be read or stored locally on your device. You can set your preferences below:

Functional cookies

These cookies enable additional functionality like saving preferences, allowing social interactions and analyzing usage for site optimization.

Advertising cookies

These cookies enable us and third parties to serve ads that are relevant to your interests.