A novel neuroscience-inspired architecture: for computer vision applications
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Institute of Electrical and Electronic Engineers
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf |
| id |
iium-50466 |
|---|---|
| recordtype |
eprints |
| spelling |
iium-504662017-01-03T08:03:15Z http://irep.iium.edu.my/50466/ A novel neuroscience-inspired architecture: for computer vision applications Hassan, Marwa Yousif Khalifa, Othman Omran Abu Talib, Azhar Olanrewaju, Rashidah Funke Hassan Abdalla Hashim, Aisha T10.5 Communication of technical information 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. Institute of Electrical and Electronic Engineers 2016 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf application/pdf en http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf 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. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7458013&tag=1 10.1109/SGCAC.2016.7458013 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
International Islamic University Malaysia |
| building |
IIUM Repository |
| collection |
Online Access |
| language |
English English |
| topic |
T10.5 Communication of technical information |
| spellingShingle |
T10.5 Communication of technical information Hassan, Marwa Yousif Khalifa, Othman Omran Abu Talib, Azhar Olanrewaju, Rashidah Funke Hassan Abdalla Hashim, Aisha A novel neuroscience-inspired architecture: for computer vision applications |
| description |
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. |
| format |
Conference or Workshop Item |
| author |
Hassan, Marwa Yousif Khalifa, Othman Omran Abu Talib, Azhar Olanrewaju, Rashidah Funke Hassan Abdalla Hashim, Aisha |
| author_facet |
Hassan, Marwa Yousif Khalifa, Othman Omran Abu Talib, Azhar Olanrewaju, Rashidah Funke Hassan Abdalla Hashim, Aisha |
| author_sort |
Hassan, Marwa Yousif |
| title |
A novel neuroscience-inspired architecture: for computer vision applications |
| title_short |
A novel neuroscience-inspired architecture: for computer vision applications |
| title_full |
A novel neuroscience-inspired architecture: for computer vision applications |
| title_fullStr |
A novel neuroscience-inspired architecture: for computer vision applications |
| title_full_unstemmed |
A novel neuroscience-inspired architecture: for computer vision applications |
| title_sort |
novel neuroscience-inspired architecture: for computer vision applications |
| publisher |
Institute of Electrical and Electronic Engineers |
| publishDate |
2016 |
| url |
http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/ http://irep.iium.edu.my/50466/1/50466_A_novel_neuroscience-inspired_architecture.pdf http://irep.iium.edu.my/50466/4/50466_A%20novel%20neuroscience_scopus.pdf |
| first_indexed |
2023-09-18T21:11:21Z |
| last_indexed |
2023-09-18T21:11:21Z |
| _version_ |
1777411273310339072 |