Publication Type : Journal Article
Publisher : Lecture Notes on Data Engineering and Communications Technologies, Springer,
Source : Lecture Notes on Data Engineering and Communications Technologies, Springer, Volume 58, p.769–778 (2021)
Url : https://www.springerprofessional.de/en/hybridization-of-trellisnet-with-cnn/19223446
Campus : Amritapuri
School : Department of Computer Science and Engineering, School of Engineering
Center : Computer Vision and Robotics
Department : Computer Science
Year : 2021
Abstract : This paper is an introduction to how hybridization is performed on a sequential model namely TrellisNet that affects its accuracy. TrellisNet is a temporal convolution Network with a special architecture. An attempt is made to combine this network with the Convolution Layer to improve Trellis Net performance. For this task, here EMNIST, which is an extension of MNIST that contains English handwritten letters and digits is used. The goal is to demonstrate the efficiency and performance of the current combined model. This also gives us an insight of performance this model as compared to other popular models used for Handwritten character recognition. TrellisNet with generalized weight matrices is a truncated Recurrent Network. Thus, a Convolution Layer followed by the defined TrellisNet is designed for achieving the targeted results aimed in this paper. This stacked architecture has delivered encouraging results. The results establish the characteristics of the model and show the problems this model can address.
Cite this Research Publication : Akshat Jaiswal, Prashanth Duvvada, and Lekha S. Nair, “Hybridization of TrellisNet with CNN”, Lecture Notes on Data Engineering and Communications Technologies, Springer, vol. 58, pp. 769–778, 2021.