Study of hierarchical learning and properties of convolution layer using sign language recognition model

Authors

  • Sagaya Mary J
  • Nachamai M
  • Nachamai M
  • .M.Vijayakumar
  • Chandra J
  • Ravi Teja Bhima

Keywords:

deep learning, convolution neural network, kernel, sparse connection, parameter sharing.

Abstract

Convolution Neural Network (CNN) as a technique improves research minds to overcome the challenges of handcrafted feature extraction and classification. CNN be a part of the representation learning methods in deep learning architecture to discover the representation needed for detection and classification automatically. So far this technique has been thought as “black boxes”, meaning that their inner working principles are mysterious and inscrutable. In order to understand the internal behavior of CNN, a model is developed on sign language recognition with 99.81%, 94.69%, 92.60% accuracy in train, test, and validation. While developing a model the inner principles of automatic feature extraction and the unique properties of convolution operations available in hierarchical CNN architecture are also learned. CNN is a multilayered network leading to feature learning and classification, it is
necessary to understand how the features are learned from each layer and how it is transformed and fed into the next higher level layers without any human interventions.

Downloads

Published

2023-12-19

How to Cite

Sagaya Mary J, Nachamai M, Nachamai M, .M.Vijayakumar, Chandra J, & Ravi Teja Bhima. (2023). Study of hierarchical learning and properties of convolution layer using sign language recognition model. Elementary Education Online, 20(5), 1118–1127. Retrieved from https://ilkogretim-online.org/index.php/pub/article/view/5029

Issue

Section

Articles