Enhancing the astrocyte spiking deep neural networks and calcium based neural network model for classification /

The ongoing challenge in machine learning is to advance general and biological inspired artificial models of neural networks which are compatible with the spatial and temporal constraints of the brain. For instance, a new term has recently been emerged to describe the communication between two neuro...

Full description

Saved in:
Bibliographic Details
Main Author: Abed, Bassam Abdul-Rahman (Author)
Format: Thesis
Language:English
Published: Kuala Lumpur : Kulliyyah of Information and Communication Technology, International Islamic University Malaysia, 2020
Subjects:
Online Access:http://studentrepo.iium.edu.my/handle/123456789/10582
Tags: Add Tag
No Tags, Be the first to tag this record!
LEADER 037980000a22003730004500
008 210319s202 my a f m 000 0 eng d
040 |a UIAM  |b eng  |e rda 
041 |a eng 
043 |a a-my--- 
100 1 |a Abed, Bassam Abdul-Rahman,  |e author 
245 1 |a Enhancing the astrocyte spiking deep neural networks and calcium based neural network model for classification /  |c by Bassam Abdul-Rahman Abed 
264 1 |a Kuala Lumpur :  |b Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,  |c 2020 
300 |a xviii, 225 leaves :  |b colour illustrations ;  |c 30cm. 
336 |2 rdacontent  |a text 
337 |2 rdamedia  |a unmediated 
337 |2 rdmedia  |a computer 
338 |2 rdacarrier  |a volume 
338 |2 rdacarrier  |a online resource 
347 |2 rdaft  |a text file  |b PDF 
500 |a Abstracts in English and Arabic. 
500 |a "A thesis submitted in fulfilment of the requirement for the degree of Doctor of Philosophy in Computer Science." --On title page. 
502 |a Thesis (Ph.D)--International Islamic University Malaysia, 2020. 
504 |a Includes bibliographical references (leaves 211-225). 
520 |a The ongoing challenge in machine learning is to advance general and biological inspired artificial models of neural networks which are compatible with the spatial and temporal constraints of the brain. For instance, a new term has recently been emerged to describe the communication between two neurons and a single astrocyte, the other type of cells in the brain, called tripartite synapse. The communication between astrocytes and astrocytes in a network called astrocytic syncytium is explored. The calcium dynamics in the brain is also considered as a significant player in brain information processing. Therefore, the study proposes to generalize mathematical models for tripartite synapse and astrocytic syncytium to advance new Tripartite Synapse Model (TSM), Artificial Astrocytic Syncytium (AAS) model and Calcium Based Artificial Neural Network (caANN) to mimic the calcium dynamics in the brain. Moreover, the study utilizes the proposed models of TSM and AAS within the architecture of the deep neural networks such as convolutional neural networks and deep belief neural networks. The simulation results of incorporating the real astrocyte in spiking response model (RSM) and Recurrent-Simple Neural Network (RSNN) has shown that astrocyte increases the postsynaptic potential and in turn, improves the RSM. Besides, the simulations of TSM in two neuron models, leaky integrate and fire (LIF) and Izhikevich model, has shown that using TSM has changed the spiking behavior (rate and firing pattern) of these models. The simulation related to the AAS by probability distribution and K-L divergence comparison has shown that the gap junction channels can be opened by the higher probability astrocytes. Finally, the result of the simulations of TSM in CNN and DBN showed that incorporating astrocytes' dynamics, properties and roles in deep learning networks compete and sometimes outperform the standard architectures of deep neural networks in terms of training and validation accuracy. 
596 |a 1 
655 7 |a Theses, IIUM local 
690 |a Dissertations, Academic  |x Kulliyyah of Information and Communication Technology  |z IIUM 
700 0 |a Amelia Ritahani Ismail,  |e degree supervisor 
700 0 |a Normaziah Abdul Aziz,  |e degree supervisor 
710 2 |a International Islamic University Malaysia.  |b Kulliyyah of Information and Communication Technology 
856 4 |u http://studentrepo.iium.edu.my/handle/123456789/10582 
900 |a sz to asbh 
999 |c 441648  |d 472182 
952 |0 0  |6 XX(566999.1)  |7 0  |8 THESES  |9 762841  |a IIUM  |b IIUM  |c MULTIMEDIA  |g 0.00  |o XX(566999.1)  |p 11100427909  |r 1900-01-02  |t 1  |v 0.00  |y THESIS