Neural Networks through Shared Maps in Mobile Devices

Abstract

We introduce a hybrid system composed of a convolutional neural network and a discrete graphical model for image recognition. This system improves upon traditional sliding window techniques for analysis of an image larger than the training data by effectively processing the full input scene through the neural network in less time. The final result is then inferred from the neural network output through energy minimization to reach a more precize localization than what traditional maximum value class comparisons yield. These results are apt for applying this process in a mobile device for real time image recognition.

Solving the Weighted Constraint Satisfaction Problems Via the Neural Network Approach

“…Hopfield neural network was introduced by Hopfield and Tank [10] [11] [13] [23]. It was first applied to solve combinatorial optimization problems.…”

IJIMAI Editor's Note - Vol. 3 Issue 1

“…The final result is then inferred from the neural network output through energy minimization to reach a more precize localization than what traditional maximum value class comparisons yield. These results are apt for applying this process in a mobile device for real time image recognition Lal, N., [5] write abour the mobile ad hoc network which is a wireless technology that contains high mobility of nodes and does not depend on the background administrator for central authority, because they do not contain any infrastructure. Nodes of the MANET use radio wave for communication and having limited resources and limited computational power.…”