Home|Journals|Articles by Year Follow on Twitter

Directory for Medical Articles
 

Open Access

Research Article

EEO. 2021; 20(5): 1118-1127


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

Sagaya Mary J, Nachamai M, Dr. M. Vijayakumar, Dr. Chandra J, Dr. Ravi Teja Bhima.

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.

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



Similar Articles

Inserting new synaptic connections into damaged neural circuits: towards synapse therapy?
Rabinowitch I
Neural regeneration research. 2022; 17(2): 300-301

Integrated molecular and affiliation network analysis: Core-periphery social clustering is associated with HIV transmission patterns.
Fujimoto K, Paraskevis D, Kuo JC, Hallmark CJ, Zhao J, Hochi A, Kuhns LM, Hwang LY, Hatzakis A, Schneider JA
Social networks. 2022; 68(): 107-117

Distribution of antibiotic resistance genes and their association with bacteria and viruses in decentralized sewage treatment facilities.
Zhao J, Li B, Lv P, Hou J, Qiu Y, Huang X
Frontiers of environmental science & engineering. 2022; 16(3): 35

Cell cycle exit and neuronal differentiation 1-engineered embryonic neural stem cells enhance neuronal differentiation and neurobehavioral recovery after experimental traumatic brain injury.
Wang R, Yang DX, Liu YL, Ding J, Guo Y, Ding WH, Tian HL, Yuan F
Neural regeneration research. 2022; 17(1): 130-136

Traumatic brain injury induced by exposure to blast overpressure via ear canal.
Ou Y, Clifton BA, Li J, Sandlin D, Li N, Wu L, Zhang C, Chen T, Huang J, Yu Y, Allison J, Fan F, Roman RJ, Shaffery J, Zhou W, Pang Y, Zhu H
Neural regeneration research. 2022; 17(1): 115-121


Full-text options


Add your Article(s) to Indexes
• citeindex.org






ScopeMed.com
CiteIndex.org
CancerLine
FoodsLine
PhytoMedline
Follow ScopeMed on Twitter
Author Tools
eJPort Journal Hosting
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (https://creativecommons.org/licenses/by-nc-sa/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
ScopeMed is a Database Service for Scientific Publications. Copyright © ScopeMed® Information Services.