Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Perfecting a Video Game with Game Metrics Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Sayed Omid Ayat
Universiti Teknologi Malaysia
Computer Science & IT Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Stochastic Computing Correlation Utilization in Convolutional Neural Network Basic Functions Hamdan Abdellatef; Mohamed Khalil Hani; Nasir Shaikh Husin; Sayed Omid Ayat
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 6: December 2018
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v16i6.8955

Abstract

In recent years, many applications have been implemented in embedded systems and mobile Internet of Things (IoT) devices that typically have constrained resources, smaller power budget, and exhibit "smartness" or intelligence. To implement computation-intensive and resource-hungry Convolutional Neural Network (CNN) in this class of devices, many research groups have developed specialized parallel accelerators using Graphical Processing Units (GPU), Field-Programmable Gate Arrays (FPGA), or Application-Specific Integrated Circuits (ASIC). An alternative computing paradigm called Stochastic Computing (SC) can implement CNN with low hardware footprint and power consumption. To enable building more efficient SC CNN, this work incorporates the CNN basic functions in SC that exploit correlation, share Random Number Generators (RNG), and is more robust to rounding error. Experimental results show our proposed solution provides significant savings in hardware footprint and increased accuracy for the SC CNN basic functions circuits compared to previous work.
A Low-complexity Complex-valued Activation Function for Fast and Accurate Spectral Domain Convolutional Neural Network Shahriyar Masud Rizvi; Ab Al-Hadi Ab Rahman; Mohamed Khalil-Hani; Sayed Omid Ayat
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 9, No 1: March 2021
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v9i1.2737

Abstract

Conventional Convolutional Neural Networks (CNNs), which are realized in spatial domain, exhibit high computational complexity. This results in high resource utilization and memory usage and makes them unsuitable for implementation in resource and energy-constrained embedded systems. A promising approach for low-complexity and high-speed solution is to apply CNN modeled in the spectral domain. One of the main challenges in this approach is the design of activation functions. Some of the proposed solutions perform activation functions in spatial domain, necessitating multiple and computationally expensive spatial-spectral domain switching. On the other hand, recent work on spectral activation functions resulted in very computationally intensive solutions. This paper proposes a complex-valued activation function for spectral domain CNNs that only transmits input values that have positive-valued real or imaginary component. This activation function is computationally inexpensive in both forward and backward propagation and provides sufficient nonlinearity that ensures high classification accuracy. We apply this complex-valued activation function in a LeNet-5 architecture and achieve an accuracy gain of up to 7% for MNIST and 6% for Fashion MNIST dataset, while providing up to 79% and 85% faster inference times, respectively, over state-of-the-art activation functions for spectral domain.
Co-Authors Ab Al-Hadi Ab Rahman Hamdan Abdellatef Mohamed Khalil Hani Mohamed Khalil-Hani Nasir Shaikh Husin Shahriyar Masud Rizvi