Related papers: A reconfigurable neural network ASIC for detector …

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and computation resource availability, we propose a novel semantic…

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been…

Despite superior performance on many computer vision tasks, deep convolution neural networks are well known to be compressed on devices that have resource constraints. Most existing network pruning methods require laborious human efforts…

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms…

Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with…

Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…

With the rapid growth of hyperspectral data archives in remote sensing (RS), the need for efficient storage has become essential, driving significant attention toward learning-based hyperspectral image (HSI) compression. However, a…

Recent clinical evidence shows a correlation between linear energy transfer (LET) and tumor control in carbon ion radiotherapy. This prompts the direct inclusion of LET into the treatment planning. Currently, LET is mainly extracted from…

Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when being trained on huge datasets. With advancing technologies, such as the Internet of Things,…

The recent advances in machine learning and deep neural networks have made them attractive candidates for wireless communications functions such as channel estimation, decoding, and downlink channel state information (CSI) compression.…

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…

Autoencoders are unsupervised neural networks that are used to process and compress input data and then reconstruct the data back to the original data size. This allows autoencoders to be used for different processing applications such as…

Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks. Most existing…

Systolic array accelerators execute CNNs with energy dominated by the switching activity of multiply accumulate (MAC) units. Although prior work exploits weight dependent MAC power for compression, existing methods often use global…

Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we…

The High Level Trigger (HLT) of the future ALICE heavy-ion experiment has to reduce its input data rate of up to 25 GB/s to at most 1.25 GB/s for output before the data is written to permanent storage. To cope with these data rates a large…

Reconstructing charged particle tracks is a fundamental task in modern collider experiments. The unprecedented particle multiplicities expected at the High-Luminosity Large Hadron Collider (HL-LHC) pose significant challenges for track…

In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy…

Compression is a standard procedure for making convolutional neural networks (CNNs) adhere to some specific computing resource constraints. However, searching for a compressed architecture typically involves a series of time-consuming…

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…