A novel neuroscience-inspired architecture: for computer vision applications

Hassan, Marwa Yousif and Khalifa, Othman Omran and Abu Talib, Azhar and Olanrewaju, Rashidah Funke and Hassan Abdalla Hashim, Aisha (2016) A novel neuroscience-inspired architecture: for computer vision applications. In: 2016 Conference of Basic Sciences and Engineering Studies (SGCAC), 20th-23rd Feb. 2016, Gam’aa Street, Khartoum, Sudan.

	PDF - Published Version Restricted to Repository staff only Download (1MB) | Request a copy
Preview	PDF (SCOPUS) Download (365kB) | Preview

Abstract

The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories is developed. The new model addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model that is followed by current deep learning systems. The validation of the proposed model was conducted using “Shape” feature dimension. The results show up to 2% accuracy rate compared to our implementation of DeepFace, a high performing face recognition algorithm that was developed by Facebook, is achieved under the same hardware/ software conditions; and we were able to speed up the training up to 21% per a training patch compared to DeepFace.

Item Type:	Conference or Workshop Item (Invited Papers)
Additional Information:	4119/50466 (ISBN: 978-1-5090-1811-6 / 978-1-5090-1812-3, DOI: 10.1109/SGCAC.2016.7458013)
Uncontrolled Keywords:	Deep learning; Neuroscience; Computer vision; Visual System; DeepFace
Subjects:	T Technology > T Technology (General) > T10.5 Communication of technical information
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering
Depositing User:	Prof. Dr Othman O. Khalifa
Date Deposited:	17 Jun 2016 15:30
Last Modified:	03 Jan 2017 16:03
URI:	http://irep.iium.edu.my/id/eprint/50466

Actions (login required)

View Item