Related papers: Optimization of Super-Directive Linear Arrays with…
This paper describes a novel approach of packing sparse convolutional neural networks for their efficient systolic array implementations. By combining subsets of columns in the original filter matrix associated with a convolutional layer,…
A general method for obtaining highly efficient factorial designs of relatively small sizes is developed for cDNA microarray experiments. The method allows the main effects and interactions of successive orders to be of possibly unequal…
Automated hyperparameter tuning aspires to facilitate the application of machine learning for non-experts. In the literature, different optimization approaches are applied for that purpose. This paper investigates the performance of…
Differential Evolution (DE) is one of the most successful and powerful evolutionary algorithms for global optimization problem. The most important operator in this algorithm is mutation operator which parents are selected randomly to…
Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently…
Differential evolution possesses a multitude of various strategies for generating new trial solutions. Unfortunately, the best strategy is not known in advance. Moreover, this strategy usually depends on the problem to be solved. This paper…
Motivated by the stringent and challenging need for `greener communications' in increasingly power-hungry 5G networks, this paper presents a detailed energy efficiency analysis for three different multi-antenna architectures, namely…
Mathematical formulations of real world optimization studies frequently present characteristics such as non-linearity, discontinuity and high complexity. This class of problems may also exhibit a high number of global minimum/maximum…
Millimeter wave (mmWave) communication is a promising technology for 5G cellular systems. To compensate for the severe path loss in mmWave systems, large antenna arrays are generally used to achieve significant beamforming gains. However,…
We propose an efficient method for designing broad beams with spatially flat array factor and efficient power utilization for cell-specific coverage in communication systems equipped with large antenna arrays. To ensure full power…
Antenna selection in Massive MIMO (Multiple Input Multiple Output) communication systems enables reduction of complexity, cost and power while keeping the channel capacity high and retaining the diversity, interference reduction, spatial…
Cell-free massive multiple-input multiple-output is a potential candidate for future networks with pervasive connectivity by utilizing coherent joint transmission and distributed antenna arrays. This paper studies the exploitation of…
This paper considers the problem of designing sparse linear tripole arrays. In such arrays at each antenna location there are three orthogonal dipoles, allowing full measurement of both the horizontal and vertical components of the received…
Future wireless communications are largely inclined to deploy massive numbers of antennas at the base stations (BSs) by leveraging cost- and energy-efficient as well as environmentally friendly antenna arrays. The emerging technology of…
Large antenna arrays can steer narrow beams towards a target area, and thus improve the communications capacity of wireless channels and the fidelity of radio sensing. Hardware that is capable of continuously-variable phase shifts is…
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the…
This work introduces NetDiff, an expressive graph denoising diffusion probabilistic architecture that generates wireless ad hoc network link topologies. Such networks, with directional antennas, can achieve unmatched performance when the…
Facing the physical limitations and energy consumption bottlenecks of traditional electronic devices, we propose an innovative design framework integrating evolutionary algorithms and metasurface technology, aiming to achieve intelligent…
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most…
Evolutionary algorithms are a type of artificial intelligence that utilize principles of evolution to efficiently determine solutions to defined problems. These algorithms are particularly powerful at finding solutions that are too complex…