Time-Reduced Model for Multilayer Spiking Neural Networks
Issue:
Volume 7, Issue 1, June 2023
Pages:
1-8
Received:
15 January 2023
Accepted:
3 February 2023
Published:
16 February 2023
Abstract: Spiking neural networks (SNNs) is a type of biological neural network model, which is more biologically plausible and computationally powerful than traditional artificial neural networks (ANNs). SNNs can achieve the same goals as ANNs, and can build a large-scale network structure (i.e. deep spiking neural network) to accomplish complex tasks. However, training deep spiking neural network is difficult due to the non-differentiable nature of spike events, and it requires much computation time during the training period. In this paper, a time-reduced model adopting two methods is presented for reducing the computation time of a deep spiking neural network (i.e. approximating the spike response function by the piecewise linear method, and choosing the suitable number of sub-synapses). The experimental results show that the methods of piecewise linear approximation and choosing the suitable number of sub-synapses is effective. This method can not only reduce the training time but also simplify the network structure. With the piecewise linear approximation method, the half of computation time of the original model can be reduced by at least. With the rule of choosing the number of sub-synapses, the computation time of less than one-tenth of the original model can be reduced for XOR and Iris tasks.
Abstract: Spiking neural networks (SNNs) is a type of biological neural network model, which is more biologically plausible and computationally powerful than traditional artificial neural networks (ANNs). SNNs can achieve the same goals as ANNs, and can build a large-scale network structure (i.e. deep spiking neural network) to accomplish complex tasks. Howe...
Show More
Research Article
Design and Implementation of an IPsec VPN Tunnel to Connect the Head Office and Branch Office of Hijra Bank
Issue:
Volume 7, Issue 1, June 2023
Pages:
9-23
Received:
25 October 2023
Accepted:
11 November 2023
Published:
24 November 2023
Abstract: Network connectivity is crucial in the banking sector for handling sensitive tasks and maintaining operational efficiency. Security issues arise when employees or business partners access internal networks from unprotected external locations. To address this, a project was implemented to ensure safe interaction between branch office hosts and head office hosts. IPsec VPN tunneling was used, utilizing Security Association (SA) establishment, shared keys, ESP protocol, SHA1 for authentication, and 3DES for encryption. Key exchange was also performed using IKE. The configuration results were tested and validated to ensure the security of the system. This study describes the planning and execution of an IPsec VPN tunnel that links Hijra Bank's main office and one of its branches. The needs and difficulties in creating a dependable and secure connection between the two locations are described in the article. The design comprises configuring IPsec protocols and security policies in addition to choosing suitable hardware and software components. The VPN tunnel is deployed and tested during the implementation process to guarantee its performance and functioning. The outcomes show that the head office and branch office were able to successfully create a secure communication channel, allowing for safe data transmission and resource access. Corporations wishing to integrate comparable VPN solutions for their network infrastructure can benefit significantly from the study's conclusions
Abstract: Network connectivity is crucial in the banking sector for handling sensitive tasks and maintaining operational efficiency. Security issues arise when employees or business partners access internal networks from unprotected external locations. To address this, a project was implemented to ensure safe interaction between branch office hosts and head ...
Show More
