Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Manylion Llyfryddiaeth
Prif Awduron:	Shahir, Rafiad Sadat, Humayun, Zayed, Tamim, Mashrufa Akter, Saha, Shouri
Awduron Eraill:	Alam, Golam Rabiul
Fformat:	Traethawd Ymchwil
Iaith:	English
Cyhoeddwyd:	Brac University 2024
Pynciau:	Artificial neural network Rapid convergence Connected hidden neurons Neural networks (Computer science)
Mynediad Ar-lein:	http://hdl.handle.net/10361/22835

id	10361-22835
record_format	dspace
spelling	10361-228352024-05-15T21:03:48Z Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence Shahir, Rafiad Sadat Humayun, Zayed Tamim, Mashrufa Akter Saha, Shouri Alam, Golam Rabiul Department of Computer Science and Engineering, Brac University Artificial neural network Rapid convergence Connected hidden neurons Neural networks (Computer science) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 17-18). Despite artificial neural networks being inspired by the functionalities of biological neural networks, unlike biological neural networks, conventional artificial neural networks are often structured hierarchically, which can impede the flow of information between neurons as the neurons in the same layer have no connections between them. Hence, we propose a more robust model of artificial neural networks where the hidden neurons, residing in the same hidden layer, are interconnected that leads to rapid convergence. With the experimental study of our proposed model as fully connected layers in deep networks, we demonstrate that the model results in a noticeable increase in convergence rate compared to the conventional feed-forward neural network. Rafiad Sadat Shahir Zayed Humayun Mashrufa Akter Tamim Shouri Saha B.Sc. in Computer Science and Engineering 2024-05-15T05:53:09Z 2024-05-15T05:53:09Z ©2023 2023-09 Thesis ID 20101580 ID 20141030 ID 20101586 ID 20101349 http://hdl.handle.net/10361/22835 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 29 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Artificial neural network Rapid convergence Connected hidden neurons Neural networks (Computer science)
spellingShingle	Artificial neural network Rapid convergence Connected hidden neurons Neural networks (Computer science) Shahir, Rafiad Sadat Humayun, Zayed Tamim, Mashrufa Akter Saha, Shouri Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.
author2	Alam, Golam Rabiul
author_facet	Alam, Golam Rabiul Shahir, Rafiad Sadat Humayun, Zayed Tamim, Mashrufa Akter Saha, Shouri
format	Thesis
author	Shahir, Rafiad Sadat Humayun, Zayed Tamim, Mashrufa Akter Saha, Shouri
author_sort	Shahir, Rafiad Sadat
title	Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
title_short	Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
title_full	Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
title_fullStr	Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
title_full_unstemmed	Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence
title_sort	connected hidden neurons (chnnet): an artificial neural network for rapid convergence
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/22835
work_keys_str_mv	AT shahirrafiadsadat connectedhiddenneuronschnnetanartificialneuralnetworkforrapidconvergence AT humayunzayed connectedhiddenneuronschnnetanartificialneuralnetworkforrapidconvergence AT tamimmashrufaakter connectedhiddenneuronschnnetanartificialneuralnetworkforrapidconvergence AT sahashouri connectedhiddenneuronschnnetanartificialneuralnetworkforrapidconvergence
_version_	1814309153553776640

Connected hidden neurons (CHNNet): an artificial neural network for rapid convergence

Eitemau Tebyg