5 Hits in 0.48 sec

Long Short-Term Memory Spiking Networks and Their Applications [article]

Ali Lotfi Rezaabad, Sriram Vishwanath
2020 arXiv   pre-print
Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with conventional backpropagation techniques. In spite of the significant progress made in training conventional deep neural networks (DNNs), training methods for SNNs still remain relatively poorly understood. In this paper, we present a novel framework for
more » ... g recurrent SNNs. Analogous to the benefits presented by recurrent neural networks (RNNs) in learning time series models within DNNs, we develop SNNs based on long short-term memory (LSTM) networks. We show that LSTM spiking networks learn the timing of the spikes and temporal dependencies. We also develop a methodology for error backpropagation within LSTM-based SNNs. The developed architecture and method for backpropagation within LSTM-based SNNs enable them to learn long-term dependencies with comparable results to conventional LSTMs.
arXiv:2007.04779v1 fatcat:edxjbezm6fabrlvct5p7czlvoa

Performance Enhancement of the Golden Code by Utilizing ORIOL Antenna [article]

Vahid Amiri, Mohammadali Sadat Hosseini, Ali Lotfi-Rezaabad, and Siamak Talebi
2016 arXiv   pre-print
In this paper, a novel method is exposed to improve the performance of the Golden code, by using octagonal reconfigurable isolated orthogonal element (ORIOL) antennas, instead of a conventional microstrip patch antenna. The aforementioned antenna, should be employed in both the transmitter and the receiver sides, to approach the mentioned improvement. As a matter fact, in this paper, we recommend space-time-polarization diversity instead of space-time singly; therefore it is obvious that by
more » ... oying the aforementioned technique, the system obtains more strength against destructive fading. The simulations for different rates have confirmed that, utilizing ORIOL antenna outperforms patch microstrip one, which is roughly about 2 to 3 dB, according to the rates.
arXiv:1605.08427v1 fatcat:kys7dwwu4bfo3hgmuemzztqoqu

Two Quasi Orthogonal Space-Time Block Codes with Better Performance and Low Complexity Decoder [article]

Ali Lotfi-Rezaabad, Siamak Talebi, Ata Chizari
2016 arXiv   pre-print
This paper presents two new space time block codes (STBCs) with quasi orthogonal structure for an open loop multi-input single-output (MISO) systems. These two codes have been designed to transmit from three or four antennas at the transmitter and be given to one antenna at the receiver. First, the proposed codes are introduced and their structures are investigated. This is followed by the demonstration of how the decoder decodes half of transmitted symbols independent of the other half. The
more » ... t part of this paper discusses the simulation results, makes performance comparison against other popular approaches and concludes that the proposed solutions offer superiority.
arXiv:1605.05901v1 fatcat:olxmy7vgbrgmpbmq3cqdpv7qi4

Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [article]

Ali Lotfi Rezaabad, Rahi Kalantari, Sriram Vishwanath, Mingyuan Zhou, Jonathan Tamir
2021 arXiv   pre-print
As a result, the objective function may reduce the input-latent-representation correlation, specifically when we use very expressive modeling tools such as deep neural networks [Rezaabad and Vishwanath  ... 
arXiv:2011.00194v2 fatcat:firbvdui4ve63mmwmeht7kksny

Ultra-Dense 5G Small Cell Deployment for Fiber and Wireless Backhaul-Aware Infrastructures [article]

Ali Lotfi Rezaabad, Hamzeh Beyranvand, Jawad A. Salehi, Martin Maier
2018 arXiv   pre-print
In this paper, we study the cell planning problem for a two-tier cellular network containing two types of base stations (BSs)-- i.e. with fiber backhaul, referred to as wired BSs (W-BSs), and BSs with wireless backhaul, referred to as unwired-BSs (U-BSs). In-band full-duplex wireless communications is used to connect U-BSs and W-BSs. We propose an algorithm to determine the minimum number of W-BSs and U-BSs to satisfy given cell and capacity coverage constraints. Furthermore, we apply our
more » ... ed non-dominated sorting genetic algorithm II (NSGA-II) to solve both cell planning and joint cell and backhaul planning problem to minimize the cost of planning, while maximizing the coverage simultaneously. Additionally, the considered cell planning program is developed into an optimization by including the problem of minimizing the cost of fiber backhaul deployment. In order to analyze the performance of the proposed algorithm, we study three different deployment scenarios based on different spatial distributions of users and coverage areas. The results show the superiority of our proposed NSGA-II algorithm for both cell planning and joint cell and backhaul planning to other well-known optimization algorithms. The results also reveal that there is a trade-off between cell deployment costs and SINR/rate coverage, and W-BSs are placed in congested areas to consume less resources for wireless backhauls. Similarly, a trade-off between cell and fiber deployment costs and SINR/rate coverage is observed in planning. We show that for realistic scenarios desirable solutions can be selected from the Pareto front of the introduced multi-objective problem based on given cellular operator policies.
arXiv:1808.01297v2 fatcat:h72hvzvwovgc7cwip227mnogwi