Related papers: Compression of Site-Specific Deep Neural Networks …

The rapid growth of deep learning models has increased the demand for efficient distributed training strategies. Fully sharded approaches like ZeRO-3 and FSDP partition model parameters across GPUs and apply optimizations such as…

Massive multiple-input multiple-output (MIMO) is a promising technology to increase link capacity and energy efficiency. However, these benefits are based on available channel state information (CSI) at the base station (BS). Therefore,…

Multivariate time series anomaly detection is a crucial problem in many industrial and research applications. Timely detection of anomalies allows, for instance, to prevent defects in manufacturing processes and failures in cyberphysical…

Assume that a multi-user multiple-input multiple-output (MIMO) communication system must be designed to cover a given area with maximal energy efficiency (bit/Joule). What are the optimal values for the number of antennas, active users, and…

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO…

Massive multiple-input multiple-output (MIMO) is a key technology for 5G wireless communications with a promise of significant capacity increase. The use of low-resolution data converters is crucial for massive MIMO to make the overall…

Hybrid precoding design can be challenging for broadband millimeter-wave (mmWave) massive MIMO due to the frequency-flat analog precoder in radio frequency (RF). Prior broadband hybrid precoding work usually focuses on fully-connected array…

Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that…

Innovation in the physical layer of communication systems has traditionally been achieved by breaking down the transceivers into sets of processing blocks, each optimized independently based on mathematical models. Conversely, deep learning…

Deep learning (DL) models can now run on microcontrollers (MCUs). Through neural architecture search (NAS), we can search DL models that meet the constraints of MCUs. Among various constraints, energy and latency costs of the model…

Hybrid analog and digital beamforming transceivers are instrumental in addressing the challenge of expensive hardware and high training overheads in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output)…

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both…

Federated Learning (FL) is commonly used in systems with distributed and heterogeneous devices with access to varying amounts of data and diverse computing and storage capacities. FL training process enables such devices to update the…

The paper describes an online deep learning algorithm (ODL) for adaptive modulation and coding in massive MIMO. The algorithm is based on a fully connected neural network, which is initially trained on the output of the traditional…

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Accurate channel knowledge is critical in massive multiple-input multiple-output (MIMO), which motivates the use of channel prediction. Machine learning techniques for channel prediction hold much promise, but current schemes are limited in…

In this work, we propose an effective scheme (called DP-Net) for compressing the deep neural networks (DNNs). It includes a novel dynamic programming (DP) based algorithm to obtain the optimal solution of weight quantization and an…

This paper studies an energy efficient design of precoders for point-to-point multiple-input-multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems. Differently from traditional approaches, the optimal power…

Training deep neural networks (DNNs) on edge devices has attracted increasing attention due to its potential to address challenges related to domain adaptation and privacy preservation. However, DNNs typically rely on large datasets for…