Related papers: Adaptive Block Floating-Point for Analog Deep Lear…

Underwater acoustic target recognition is critical for maritime applications, yet it faces challenges arising from the complex and diverse nature of ship-radiated noise. To address these issues, we propose a robust deep learning-based…

Federated learning has significantly advanced distributed training of machine learning models across decentralized data sources. However, existing frameworks often lack comprehensive solutions that combine uncertainty quantification,…

Systolic array-based deep neural network (DNN) accelerators have recently gained prominence for their low computational cost. However, their high energy consumption poses a bottleneck to their deployment in energy-constrained devices. To…

Implementations of artificial neural networks (ANNs) might lead to failures, which are hardly predicted in the design phase since ANNs are highly parallel and their parameters are barely interpretable. Here, we develop and evaluate a novel…

Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device…

The discrete Fourier transform (DFT) is widely employed for multi-beam digital beamforming. The DFT can be efficiently implemented through the use of fast Fourier transform (FFT) algorithms, thus reducing chip area, power consumption,…

While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) the mismatch between…

Reliability issues stemming from device level non-idealities of non-volatile emerging technologies like ferroelectric field-effect transistors (FeFET), especially at scaled dimensions, cause substantial degradation in the accuracy of…

An inverse method for parameters estimation of infinite cylinders (the dielectric properties, location, and radius) in two dimensions from amplitude-only microwave information is presented. To this end two different Artificial Neural…

Transformers have emerged as a powerful tool for natural language processing (NLP) and computer vision. Through the attention mechanism, these models have exhibited remarkable performance gains when compared to conventional approaches like…

We propose an adaptive learning-based framework for uplink massive multiple-input multiple-output (MIMO) systems with one-bit analog-to-digital converters. Learning-based detection does not need to estimate channels, which overcomes a key…

Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels…

Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their high computational and memory requirements. Spiking neural…

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible…

Neural networks (NNs) are increasingly employed in safety-critical domains and in environments prone to unreliability (e.g., soft errors), such as on spacecraft. Therefore, it is critical to impart fault tolerance to NN inference.…

Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may…

The frequency-domain approach (FDA) to transient analysis of the boundary element method, although is appealing for engineering applications, is computationally expensive. This paper proposes a novel adaptive frequency sampling (AFS)…

Floating-point accumulation networks (FPANs) are key building blocks used in many floating-point algorithms, including compensated summation and double-double arithmetic. FPANs are notoriously difficult to analyze, and algorithms using…

We present a high-speed, energy-efficient Convolutional Neural Network (CNN) architecture utilising the capabilities of a unique class of devices known as analog Focal Plane Sensor Processors (FPSP), in which the sensor and the processor…

A space-time adaptive decision feedback (DF) receiver using recurrent neural networks (RNN) is proposed for joint equalization and interference suppression in direct-sequence code-division-multiple-access (DS-CDMA) systems equipped with…