Related papers: Advanced Equalization in 112 Gb/s Upstream PON Usi…
Linear and nonlinear distortions in optical communication signals are equalized using an integrated feed-forward Photonic Neural Network (PNN). The PNN is based on a linear stage made of an 8-tap Finite Impulse Response (FIR) filter,…
Since current neural network development systems in Xilinx and VLSI require codevelopment with Python libraries, the first stage of a convolutional network has been implemented by developing a convolutional layer entirely in Verilog. This…
FPGA accelerators for lightweight neural convolutional networks (LWCNNs) have recently attracted significant attention. Most existing LWCNN accelerators focus on single-Computing-Engine (CE) architecture with local optimization. However,…
This paper studies the computational offloading of CNN inference in device-edge co-inference systems. Inspired by the emerging paradigm semantic communication, we propose a novel autoencoder-based CNN architecture (AECNN), for effective…
In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the…
FPN (Feature Pyramid Network) has become a basic component of most SoTA one stage object detectors. Many previous studies have repeatedly proved that FPN can caputre better multi-scale feature maps to more precisely describe objects if they…
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…
Efficient detectors for edge devices are often optimized for parameters or speed count metrics, which remain in weak correlation with the energy of detectors. However, some vision applications of convolutional neural networks, such as…
The evolution toward sixth-generation (6G) wireless networks demands high-performance transceiver architectures capable of handling complex and dynamic environments. Conventional orthogonal frequency-division multiplexing (OFDM) receivers…
This paper proposes a novel foreground linearization scheme for a high-speed CS-DAC. The technique leverages neural networks (NNs) to derive a LUT that maps the inverse of the DAC transfer characteristic onto the input codes. The algorithm…
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, ``classical'' federated learning…
Majority of deep learning methods utilize vanilla convolution for enhancing underwater images. While vanilla convolution excels in capturing local features and learning the spatial hierarchical structure of images, it tends to smooth input…
In this paper, we investigate the performance of a three-node dual-hop cognitive radio network (CRN) with a half-duplex (HD) decode-and-forward (DF) buffer-aided relay. We derive expressions for the average rate and symbol error rate (SER)…
Deep Operator Networks (DeepONets) have recently emerged as powerful data-driven frameworks for learning nonlinear operators, particularly suited for approximating solutions to partial differential equations. Despite their promising…
The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…
Reliable digital twins of lithium-ion batteries must achieve high physical fidelity with sub-millisecond speed. In this work, we benchmark three operator-learning surrogates for the Single Particle Model (SPM): Deep Operator Networks…
A femtosecond frequency comb provides a vast number of equidistantly spaced narrow band laser modes that can be simultaneously tuned and frequency calibrated with 15 digits accuracy. Our Vernier spectrometer utilizes all of theses modes in…
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated…
Neural networks are essential components of learning-based software systems. However, their high compute, memory, and power requirements make using them in low resources domains challenging. For this reason, neural networks are often…
There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some…