Multi-Column Convolution Neural Network Model Based on Adaptive Enhancement

Author(s):  
YiLiang Shi ◽  
Zhenghong Yu
Author(s):  
Olga Uvarova ◽  
Sergey Uvarov

The paper considers a mechanism for constructing a model based on artificial neural network for obtaining the values of the cohesive energy of a system of atoms. Cohesive energy allows for calculation of total energy of system. It is one of the most important characteristics of a structure. A computational experiment is carried out for one-component crystal structures of Si, Ge and C.


Offline Signature recognition plays an important role in Forensic issues. In this paper, we explore Signature Identification and Verification using features extracted from pretrained Convolution Neural Network model (Alex Net). All the experiments are performed on signatures from three dataset (SigComp2011) (Dutch, Chinese), SigWiComp2013 (Japanese) and SigWIcomp2015 (Italian). The result shows that features extracted from pretrained Deep Convolution neural network and SVM as classifier show better results than that of Decision Tree. The accuracy of more than 96% for Japanese, Italian, Dutch and Chinese Signatures is obtained with Deep Convolution neural network and SVM as classifier.


Sign in / Sign up

Export Citation Format

Share Document