| Title |
An Implementation of Generalized Second-Order Neural Networks for Pattern Recognition |
| Authors |
이봉규(Lee Bong-Kyu) ; 양요한(Yang Yo-Han) |
| Keywords |
translation invariant ; generalization ; second-order neural network ; weight constraint ; pixel combination |
| Abstract |
For most of pattern recognition applications, it is required to correctly recognize patterns even if they have translation variations. In this paper, to achieve the goal of translation invariant pattern recognition, we propose a new generalized translation invariant second-order neural network using a constraint on the weights. The weight constraint is implemented using generalized translation invariant features which are accumulated sums of pixel combinations. Simulation results will be given to demonstrate that the proposed second-order neural network has the generalized translation invariant property. |